Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5036 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5228. Min Range: -7.5228
Max Act: 7.5228. Min Act: -0.1700
Data Index: 719283 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5228. Min Range: -7.5228
Max Act: 7.4603. Min Act: -0.1700
Data Index: 260749 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5228. Min Range: -7.5228
Max Act: 7.3978. Min Act: -0.1700
Data Index: 6219193 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5228. Min Range: -7.5228
Max Act: 7.3665. Min Act: -0.1700
Data Index: 850189 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5228. Min Range: -7.5228
Max Act: 7.3665. Min Act: -0.1700
Data Index: 1910433 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5228. Min Range: -7.5228
Max Act: 7.3353. Min Act: -0.1700
Data Index: 836793 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5228. Min Range: -7.5228
Max Act: 7.2728. Min Act: -0.1700
Data Index: 7948496 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5228. Min Range: -7.5228
Max Act: 7.1790. Min Act: -0.1700
Data Index: 2162071 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5228. Min Range: -7.5228
Max Act: 7.1790. Min Act: -0.1700
Data Index: 7177303 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5228. Min Range: -7.5228
Max Act: 7.1165. Min Act: -0.1700
Data Index: 2379042 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5228. Min Range: -7.5228
Max Act: 7.0228. Min Act: -0.1700
Data Index: 8822685 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5228. Min Range: -7.5228
Max Act: 7.0540. Min Act: -0.1700
Data Index: 608242 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5228. Min Range: -7.5228
Max Act: 7.0540. Min Act: -0.1700
Data Index: 2555535 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5228. Min Range: -7.5228
Max Act: 7.0540. Min Act: -0.1700
Data Index: 4030780 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5228. Min Range: -7.5228
Max Act: 7.0228. Min Act: -0.1700
Data Index: 5662938 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5228. Min Range: -7.5228
Max Act: 7.0228. Min Act: -0.1700
Data Index: 6468478 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5228. Min Range: -7.5228
Max Act: 6.9603. Min Act: -0.1700
Data Index: 6613689 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5228. Min Range: -7.5228
Max Act: 7.0228. Min Act: -0.1700
Data Index: 924776 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5228. Min Range: -7.5228
Max Act: 6.9915. Min Act: -0.1700
Data Index: 125897 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5228. Min Range: -7.5228
Max Act: 6.9603. Min Act: -0.1700
Data Index: 850188 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #19