Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 396 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.5879. Min Range: -7.5879
Max Act: 7.5879. Min Act: -0.1700
Data Index: 6358563 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5879. Min Range: -7.5879
Max Act: 7.2754. Min Act: -0.1700
Data Index: 342498 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5879. Min Range: -7.5879
Max Act: 7.1816. Min Act: -0.1700
Data Index: 3158036 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5879. Min Range: -7.5879
Max Act: 7.1504. Min Act: -0.1700
Data Index: 261969 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5879. Min Range: -7.5879
Max Act: 7.0566. Min Act: -0.1700
Data Index: 6026657 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5879. Min Range: -7.5879
Max Act: 7.0254. Min Act: -0.1700
Data Index: 4311555 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5879. Min Range: -7.5879
Max Act: 6.9004. Min Act: -0.1700
Data Index: 866789 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5879. Min Range: -7.5879
Max Act: 6.8691. Min Act: -0.1700
Data Index: 4163717 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5879. Min Range: -7.5879
Max Act: 6.9004. Min Act: -0.1700
Data Index: 1626676 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5879. Min Range: -7.5879
Max Act: 6.8379. Min Act: -0.1700
Data Index: 5028102 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5879. Min Range: -7.5879
Max Act: 6.8691. Min Act: -0.1700
Data Index: 866791 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5879. Min Range: -7.5879
Max Act: 6.8066. Min Act: -0.1700
Data Index: 3787326 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5879. Min Range: -7.5879
Max Act: 6.8066. Min Act: -0.1700
Data Index: 1069194 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5879. Min Range: -7.5879
Max Act: 6.7754. Min Act: -0.1700
Data Index: 8140898 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5879. Min Range: -7.5879
Max Act: 6.7754. Min Act: -0.1700
Data Index: 1545162 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5879. Min Range: -7.5879
Max Act: 6.7754. Min Act: -0.1700
Data Index: 7722890 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5879. Min Range: -7.5879
Max Act: 6.7754. Min Act: -0.1700
Data Index: 3383001 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5879. Min Range: -7.5879
Max Act: 6.7754. Min Act: -0.1700
Data Index: 624597 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5879. Min Range: -7.5879
Max Act: 6.7441. Min Act: -0.1700
Data Index: 261993 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5879. Min Range: -7.5879
Max Act: 6.7129. Min Act: -0.1700
Data Index: 436842 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #19