Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4345 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.5159. Min Range: -3.5159
Max Act: 3.5159. Min Act: -0.1700
Data Index: 661845 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5159. Min Range: -3.5159
Max Act: 3.5159. Min Act: -0.1700
Data Index: 1913083 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5159. Min Range: -3.5159
Max Act: 3.4845. Min Act: -0.1700
Data Index: 4331586 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5159. Min Range: -3.5159
Max Act: 3.4532. Min Act: -0.1700
Data Index: 4415222 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5159. Min Range: -3.5159
Max Act: 3.4532. Min Act: -0.1700
Data Index: 3145536 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5159. Min Range: -3.5159
Max Act: 3.4532. Min Act: -0.1700
Data Index: 7944967 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5159. Min Range: -3.5159
Max Act: 3.4532. Min Act: -0.1700
Data Index: 696164 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5159. Min Range: -3.5159
Max Act: 3.4219. Min Act: -0.1700
Data Index: 6416615 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5159. Min Range: -3.5159
Max Act: 3.3905. Min Act: -0.1700
Data Index: 1000404 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5159. Min Range: -3.5159
Max Act: 3.4219. Min Act: -0.1700
Data Index: 948979 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5159. Min Range: -3.5159
Max Act: 3.4219. Min Act: -0.1700
Data Index: 2747450 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5159. Min Range: -3.5159
Max Act: 3.4219. Min Act: -0.1700
Data Index: 2067578 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5159. Min Range: -3.5159
Max Act: 3.3905. Min Act: -0.1700
Data Index: 4049024 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5159. Min Range: -3.5159
Max Act: 3.3905. Min Act: -0.1700
Data Index: 622141 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5159. Min Range: -3.5159
Max Act: 3.3905. Min Act: -0.1700
Data Index: 2380787 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5159. Min Range: -3.5159
Max Act: 3.3278. Min Act: -0.1700
Data Index: 7130600 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5159. Min Range: -3.5159
Max Act: 3.3591. Min Act: -0.1700
Data Index: 3659550 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5159. Min Range: -3.5159
Max Act: 3.3591. Min Act: -0.1700
Data Index: 4415226 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5159. Min Range: -3.5159
Max Act: 3.3591. Min Act: -0.1700
Data Index: 6189950 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5159. Min Range: -3.5159
Max Act: 3.3278. Min Act: -0.1700
Data Index: 3059665 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #19