Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.6147. Min Range: -4.6147
Max Act: 4.6147. Min Act: -0.1700
Data Index: 8777960 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6147. Min Range: -4.6147
Max Act: 4.5209. Min Act: -0.1700
Data Index: 6640295 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6147. Min Range: -4.6147
Max Act: 4.4584. Min Act: -0.1700
Data Index: 6944919 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6147. Min Range: -4.6147
Max Act: 4.4272. Min Act: -0.1700
Data Index: 3614879 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6147. Min Range: -4.6147
Max Act: 4.4272. Min Act: -0.1700
Data Index: 7433410 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6147. Min Range: -4.6147
Max Act: 4.3959. Min Act: -0.1700
Data Index: 1881584 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6147. Min Range: -4.6147
Max Act: 4.3022. Min Act: -0.1700
Data Index: 3485628 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6147. Min Range: -4.6147
Max Act: 4.2709. Min Act: -0.1700
Data Index: 306707 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6147. Min Range: -4.6147
Max Act: 4.2709. Min Act: -0.1700
Data Index: 3239709 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6147. Min Range: -4.6147
Max Act: 4.2709. Min Act: -0.1700
Data Index: 5463313 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6147. Min Range: -4.6147
Max Act: 4.2396. Min Act: -0.1700
Data Index: 5704668 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6147. Min Range: -4.6147
Max Act: 4.2709. Min Act: -0.1700
Data Index: 6624127 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6147. Min Range: -4.6147
Max Act: 4.2709. Min Act: -0.1700
Data Index: 3648524 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6147. Min Range: -4.6147
Max Act: 4.2396. Min Act: -0.1700
Data Index: 161905 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6147. Min Range: -4.6147
Max Act: 4.2396. Min Act: -0.1700
Data Index: 7562940 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6147. Min Range: -4.6147
Max Act: 4.2396. Min Act: -0.1700
Data Index: 334523 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6147. Min Range: -4.6147
Max Act: 4.2396. Min Act: -0.1700
Data Index: 4259285 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6147. Min Range: -4.6147
Max Act: 4.2084. Min Act: -0.1700
Data Index: 5214128 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6147. Min Range: -4.6147
Max Act: 4.2084. Min Act: -0.1700
Data Index: 6495770 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6147. Min Range: -4.6147
Max Act: 4.2084. Min Act: -0.1700
Data Index: 1763288 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #19