Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4033 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2151. Min Range: -6.2151
Max Act: 6.2151. Min Act: -0.1700
Data Index: 1164212 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2151. Min Range: -6.2151
Max Act: 6.0901. Min Act: -0.1700
Data Index: 8601528 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2151. Min Range: -6.2151
Max Act: 6.0901. Min Act: -0.1700
Data Index: 3208999 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2151. Min Range: -6.2151
Max Act: 6.0901. Min Act: -0.1700
Data Index: 4921165 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2151. Min Range: -6.2151
Max Act: 6.0588. Min Act: -0.1700
Data Index: 1934190 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2151. Min Range: -6.2151
Max Act: 6.0276. Min Act: -0.1700
Data Index: 3190408 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2151. Min Range: -6.2151
Max Act: 6.0276. Min Act: -0.1700
Data Index: 4370548 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2151. Min Range: -6.2151
Max Act: 5.9651. Min Act: -0.1700
Data Index: 4171094 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2151. Min Range: -6.2151
Max Act: 5.9651. Min Act: -0.1700
Data Index: 4278610 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2151. Min Range: -6.2151
Max Act: 5.9338. Min Act: -0.1700
Data Index: 8381365 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2151. Min Range: -6.2151
Max Act: 5.9338. Min Act: -0.1700
Data Index: 1105966 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2151. Min Range: -6.2151
Max Act: 5.9651. Min Act: -0.1700
Data Index: 4794806 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2151. Min Range: -6.2151
Max Act: 5.9338. Min Act: -0.1700
Data Index: 2534170 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2151. Min Range: -6.2151
Max Act: 5.9026. Min Act: -0.1700
Data Index: 3706653 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2151. Min Range: -6.2151
Max Act: 5.9026. Min Act: -0.1700
Data Index: 8458344 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2151. Min Range: -6.2151
Max Act: 5.9026. Min Act: -0.1700
Data Index: 5414516 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2151. Min Range: -6.2151
Max Act: 5.8713. Min Act: -0.1700
Data Index: 7222016 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2151. Min Range: -6.2151
Max Act: 5.8713. Min Act: -0.1700
Data Index: 2894461 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2151. Min Range: -6.2151
Max Act: 5.8088. Min Act: -0.1700
Data Index: 7125495 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2151. Min Range: -6.2151
Max Act: 5.8088. Min Act: -0.1700
Data Index: 330622 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #19