Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2357 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 10.6530. Min Range: -10.6530
Max Act: 10.6530. Min Act: -0.1700
Data Index: 3113004 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.6530. Min Range: -10.6530
Max Act: 10.4655. Min Act: -0.1700
Data Index: 8800506 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.6530. Min Range: -10.6530
Max Act: 10.4030. Min Act: -0.1700
Data Index: 1528164 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.6530. Min Range: -10.6530
Max Act: 10.4030. Min Act: -0.1700
Data Index: 5403274 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.6530. Min Range: -10.6530
Max Act: 10.4030. Min Act: -0.1700
Data Index: 2019271 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.6530. Min Range: -10.6530
Max Act: 10.3405. Min Act: -0.1700
Data Index: 4571693 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.6530. Min Range: -10.6530
Max Act: 10.3405. Min Act: -0.1700
Data Index: 6112622 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.6530. Min Range: -10.6530
Max Act: 10.2780. Min Act: -0.1700
Data Index: 104222 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.6530. Min Range: -10.6530
Max Act: 10.2780. Min Act: -0.1700
Data Index: 8105504 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.6530. Min Range: -10.6530
Max Act: 10.2155. Min Act: -0.1700
Data Index: 1156398 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.6530. Min Range: -10.6530
Max Act: 10.2155. Min Act: -0.1700
Data Index: 8708276 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.6530. Min Range: -10.6530
Max Act: 10.2155. Min Act: -0.1700
Data Index: 799447 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.6530. Min Range: -10.6530
Max Act: 10.2155. Min Act: -0.1700
Data Index: 1528165 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.6530. Min Range: -10.6530
Max Act: 10.1530. Min Act: -0.1700
Data Index: 2388041 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.6530. Min Range: -10.6530
Max Act: 10.1530. Min Act: -0.1700
Data Index: 621293 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.6530. Min Range: -10.6530
Max Act: 10.1530. Min Act: -0.1700
Data Index: 3759190 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.6530. Min Range: -10.6530
Max Act: 10.0905. Min Act: -0.1700
Data Index: 3735682 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.6530. Min Range: -10.6530
Max Act: 10.0905. Min Act: -0.1700
Data Index: 1504081 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.6530. Min Range: -10.6530
Max Act: 10.0905. Min Act: -0.1700
Data Index: 7164411 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.6530. Min Range: -10.6530
Max Act: 10.0280. Min Act: -0.1700
Data Index: 3783990 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #19