Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4665 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6594. Min Range: -4.6594
Max Act: 4.6594. Min Act: -0.1700
Data Index: 3769579 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6594. Min Range: -4.6594
Max Act: 4.5344. Min Act: -0.1700
Data Index: 3046379 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6594. Min Range: -4.6594
Max Act: 4.4719. Min Act: -0.1700
Data Index: 6230130 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6594. Min Range: -4.6594
Max Act: 4.4407. Min Act: -0.1700
Data Index: 5675645 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6594. Min Range: -4.6594
Max Act: 4.2844. Min Act: -0.1700
Data Index: 5095894 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6594. Min Range: -4.6594
Max Act: 4.2844. Min Act: -0.1700
Data Index: 7744992 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6594. Min Range: -4.6594
Max Act: 4.2219. Min Act: -0.1700
Data Index: 8047408 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6594. Min Range: -4.6594
Max Act: 4.2532. Min Act: -0.1700
Data Index: 6110825 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6594. Min Range: -4.6594
Max Act: 4.2532. Min Act: -0.1700
Data Index: 7584432 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6594. Min Range: -4.6594
Max Act: 4.1907. Min Act: -0.1700
Data Index: 3303410 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6594. Min Range: -4.6594
Max Act: 4.1594. Min Act: -0.1700
Data Index: 523345 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6594. Min Range: -4.6594
Max Act: 4.1282. Min Act: -0.1700
Data Index: 2903073 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6594. Min Range: -4.6594
Max Act: 4.1594. Min Act: -0.1700
Data Index: 373428 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6594. Min Range: -4.6594
Max Act: 4.1594. Min Act: -0.1700
Data Index: 755586 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6594. Min Range: -4.6594
Max Act: 4.1282. Min Act: -0.1700
Data Index: 8179499 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6594. Min Range: -4.6594
Max Act: 4.1907. Min Act: -0.1700
Data Index: 2794450 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6594. Min Range: -4.6594
Max Act: 4.1282. Min Act: -0.1700
Data Index: 6330638 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6594. Min Range: -4.6594
Max Act: 4.0969. Min Act: -0.1700
Data Index: 2952598 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6594. Min Range: -4.6594
Max Act: 4.0969. Min Act: -0.1700
Data Index: 3728717 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6594. Min Range: -4.6594
Max Act: 4.0656. Min Act: -0.1700
Data Index: 1189031 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #19