Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4832 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3915. Min Range: -7.3915
Max Act: 7.3915. Min Act: -0.1700
Data Index: 3141376 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3915. Min Range: -7.3915
Max Act: 7.2353. Min Act: -0.1700
Data Index: 6969333 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3915. Min Range: -7.3915
Max Act: 7.0478. Min Act: -0.1700
Data Index: 8315168 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3915. Min Range: -7.3915
Max Act: 7.0165. Min Act: -0.1700
Data Index: 101364 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3915. Min Range: -7.3915
Max Act: 7.0165. Min Act: -0.1700
Data Index: 3291327 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3915. Min Range: -7.3915
Max Act: 6.9540. Min Act: -0.1700
Data Index: 6969340 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3915. Min Range: -7.3915
Max Act: 6.9228. Min Act: -0.1700
Data Index: 5006670 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3915. Min Range: -7.3915
Max Act: 6.9228. Min Act: -0.1700
Data Index: 2199103 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3915. Min Range: -7.3915
Max Act: 6.7978. Min Act: -0.1700
Data Index: 5402198 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3915. Min Range: -7.3915
Max Act: 6.6728. Min Act: -0.1700
Data Index: 6865624 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3915. Min Range: -7.3915
Max Act: 6.7040. Min Act: -0.1700
Data Index: 6969341 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3915. Min Range: -7.3915
Max Act: 6.6415. Min Act: -0.1700
Data Index: 743991 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3915. Min Range: -7.3915
Max Act: 6.5790. Min Act: -0.1700
Data Index: 4595692 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3915. Min Range: -7.3915
Max Act: 6.5790. Min Act: -0.1700
Data Index: 4245992 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3915. Min Range: -7.3915
Max Act: 6.5790. Min Act: -0.1700
Data Index: 8419391 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3915. Min Range: -7.3915
Max Act: 6.5790. Min Act: -0.1700
Data Index: 6479180 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3915. Min Range: -7.3915
Max Act: 6.5478. Min Act: -0.1700
Data Index: 6969338 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3915. Min Range: -7.3915
Max Act: 6.5165. Min Act: -0.1700
Data Index: 4875260 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3915. Min Range: -7.3915
Max Act: 6.4853. Min Act: -0.1700
Data Index: 6502663 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3915. Min Range: -7.3915
Max Act: 6.4853. Min Act: -0.1700
Data Index: 4072662 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #19