Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2996 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9039. Min Range: -7.9039
Max Act: 7.9039. Min Act: -0.1700
Data Index: 7543844 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9039. Min Range: -7.9039
Max Act: 7.5914. Min Act: -0.1700
Data Index: 3630733 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9039. Min Range: -7.9039
Max Act: 7.4351. Min Act: -0.1700
Data Index: 7446738 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9039. Min Range: -7.9039
Max Act: 7.4664. Min Act: -0.1700
Data Index: 53462 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9039. Min Range: -7.9039
Max Act: 7.4351. Min Act: -0.1700
Data Index: 2413931 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9039. Min Range: -7.9039
Max Act: 7.3414. Min Act: -0.1700
Data Index: 8542779 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9039. Min Range: -7.9039
Max Act: 7.3414. Min Act: -0.1700
Data Index: 4383729 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9039. Min Range: -7.9039
Max Act: 7.3414. Min Act: -0.1700
Data Index: 3219253 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9039. Min Range: -7.9039
Max Act: 7.2476. Min Act: -0.1700
Data Index: 7892963 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9039. Min Range: -7.9039
Max Act: 7.2476. Min Act: -0.1700
Data Index: 3636395 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9039. Min Range: -7.9039
Max Act: 7.2164. Min Act: -0.1700
Data Index: 2805622 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9039. Min Range: -7.9039
Max Act: 7.2164. Min Act: -0.1700
Data Index: 1811053 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9039. Min Range: -7.9039
Max Act: 7.2164. Min Act: -0.1700
Data Index: 2419792 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9039. Min Range: -7.9039
Max Act: 7.2164. Min Act: -0.1700
Data Index: 7877800 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9039. Min Range: -7.9039
Max Act: 7.1851. Min Act: -0.1700
Data Index: 405544 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9039. Min Range: -7.9039
Max Act: 7.2164. Min Act: -0.1700
Data Index: 4560268 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9039. Min Range: -7.9039
Max Act: 7.1539. Min Act: -0.1700
Data Index: 2193609 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9039. Min Range: -7.9039
Max Act: 7.1539. Min Act: -0.1700
Data Index: 3108361 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9039. Min Range: -7.9039
Max Act: 7.1539. Min Act: -0.1700
Data Index: 5939708 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9039. Min Range: -7.9039
Max Act: 7.1851. Min Act: -0.1700
Data Index: 5544554 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #19