Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1463 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.7867. Min Range: -3.7867
Max Act: 3.7867. Min Act: -0.1700
Data Index: 7433029 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7867. Min Range: -3.7867
Max Act: 3.7554. Min Act: -0.1700
Data Index: 1080400 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7867. Min Range: -3.7867
Max Act: 3.6146. Min Act: -0.1700
Data Index: 1252112 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7867. Min Range: -3.7867
Max Act: 3.5833. Min Act: -0.1700
Data Index: 4654202 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7867. Min Range: -3.7867
Max Act: 3.5833. Min Act: -0.1700
Data Index: 4685469 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7867. Min Range: -3.7867
Max Act: 3.5833. Min Act: -0.1700
Data Index: 2235193 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7867. Min Range: -3.7867
Max Act: 3.5676. Min Act: -0.1700
Data Index: 512582 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7867. Min Range: -3.7867
Max Act: 3.5676. Min Act: -0.1700
Data Index: 3642638 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7867. Min Range: -3.7867
Max Act: 3.5676. Min Act: -0.1700
Data Index: 3733784 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7867. Min Range: -3.7867
Max Act: 3.5833. Min Act: -0.1700
Data Index: 2713925 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7867. Min Range: -3.7867
Max Act: 3.5676. Min Act: -0.1700
Data Index: 8011036 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7867. Min Range: -3.7867
Max Act: 3.5520. Min Act: -0.1700
Data Index: 7385853 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7867. Min Range: -3.7867
Max Act: 3.5050. Min Act: -0.1700
Data Index: 4377363 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7867. Min Range: -3.7867
Max Act: 3.5520. Min Act: -0.1700
Data Index: 3340549 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7867. Min Range: -3.7867
Max Act: 3.5520. Min Act: -0.1700
Data Index: 7501704 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7867. Min Range: -3.7867
Max Act: 3.5207. Min Act: -0.1700
Data Index: 4599129 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7867. Min Range: -3.7867
Max Act: 3.5363. Min Act: -0.1700
Data Index: 2235194 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7867. Min Range: -3.7867
Max Act: 3.5363. Min Act: -0.1700
Data Index: 757549 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7867. Min Range: -3.7867
Max Act: 3.5207. Min Act: -0.1700
Data Index: 1234214 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7867. Min Range: -3.7867
Max Act: 3.5363. Min Act: -0.1700
Data Index: 5395584 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #19