Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2756 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.6601. Min Range: -10.6601
Max Act: 10.6601. Min Act: -0.1700
Data Index: 2729413 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.6601. Min Range: -10.6601
Max Act: 10.5351. Min Act: -0.1700
Data Index: 3462403 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.6601. Min Range: -10.6601
Max Act: 10.4101. Min Act: -0.1700
Data Index: 6520175 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.6601. Min Range: -10.6601
Max Act: 10.2226. Min Act: -0.1700
Data Index: 291456 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.6601. Min Range: -10.6601
Max Act: 10.1601. Min Act: -0.1700
Data Index: 1861122 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.6601. Min Range: -10.6601
Max Act: 10.2226. Min Act: -0.1700
Data Index: 1915904 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.6601. Min Range: -10.6601
Max Act: 10.1601. Min Act: -0.1700
Data Index: 7390725 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.6601. Min Range: -10.6601
Max Act: 10.1601. Min Act: -0.1700
Data Index: 2912494 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.6601. Min Range: -10.6601
Max Act: 10.1601. Min Act: -0.1700
Data Index: 910681 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.6601. Min Range: -10.6601
Max Act: 10.0976. Min Act: -0.1700
Data Index: 3084096 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.6601. Min Range: -10.6601
Max Act: 10.0976. Min Act: -0.1700
Data Index: 4622751 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.6601. Min Range: -10.6601
Max Act: 10.0351. Min Act: -0.1700
Data Index: 7918031 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.6601. Min Range: -10.6601
Max Act: 10.0351. Min Act: -0.1700
Data Index: 7977926 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.6601. Min Range: -10.6601
Max Act: 9.9726. Min Act: -0.1700
Data Index: 3198702 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.6601. Min Range: -10.6601
Max Act: 9.9726. Min Act: -0.1700
Data Index: 8134048 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.6601. Min Range: -10.6601
Max Act: 9.9726. Min Act: -0.1700
Data Index: 480161 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.6601. Min Range: -10.6601
Max Act: 10.0351. Min Act: -0.1700
Data Index: 352849 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.6601. Min Range: -10.6601
Max Act: 9.9726. Min Act: -0.1700
Data Index: 2266374 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.6601. Min Range: -10.6601
Max Act: 9.9101. Min Act: -0.1700
Data Index: 4096741 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.6601. Min Range: -10.6601
Max Act: 9.8476. Min Act: -0.1700
Data Index: 5540795 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #19