Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2815 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5567. Min Range: -6.5567
Max Act: 6.5567. Min Act: -0.1700
Data Index: 3426197 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5567. Min Range: -6.5567
Max Act: 6.4005. Min Act: -0.1700
Data Index: 8805053 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5567. Min Range: -6.5567
Max Act: 6.3380. Min Act: -0.1700
Data Index: 280542 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5567. Min Range: -6.5567
Max Act: 6.3380. Min Act: -0.1700
Data Index: 6804706 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5567. Min Range: -6.5567
Max Act: 6.3067. Min Act: -0.1700
Data Index: 4476640 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5567. Min Range: -6.5567
Max Act: 6.2442. Min Act: -0.1700
Data Index: 3902847 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5567. Min Range: -6.5567
Max Act: 6.2442. Min Act: -0.1700
Data Index: 3297254 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5567. Min Range: -6.5567
Max Act: 6.2130. Min Act: -0.1700
Data Index: 4238906 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5567. Min Range: -6.5567
Max Act: 6.2130. Min Act: -0.1700
Data Index: 3756828 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5567. Min Range: -6.5567
Max Act: 6.2130. Min Act: -0.1700
Data Index: 67355 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5567. Min Range: -6.5567
Max Act: 6.1505. Min Act: -0.1700
Data Index: 1149453 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5567. Min Range: -6.5567
Max Act: 6.1817. Min Act: -0.1700
Data Index: 8410751 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5567. Min Range: -6.5567
Max Act: 6.1817. Min Act: -0.1700
Data Index: 1061031 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5567. Min Range: -6.5567
Max Act: 6.1505. Min Act: -0.1700
Data Index: 1807064 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5567. Min Range: -6.5567
Max Act: 6.1505. Min Act: -0.1700
Data Index: 4519589 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5567. Min Range: -6.5567
Max Act: 6.1192. Min Act: -0.1700
Data Index: 576048 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5567. Min Range: -6.5567
Max Act: 6.1192. Min Act: -0.1700
Data Index: 4483391 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5567. Min Range: -6.5567
Max Act: 6.1192. Min Act: -0.1700
Data Index: 813710 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5567. Min Range: -6.5567
Max Act: 6.1192. Min Act: -0.1700
Data Index: 6166972 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5567. Min Range: -6.5567
Max Act: 6.1192. Min Act: -0.1700
Data Index: 1244167 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #19