Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4261 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.6552. Min Range: -4.6552
Max Act: 4.6552. Min Act: -0.1700
Data Index: 1013917 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6552. Min Range: -4.6552
Max Act: 4.6552. Min Act: -0.1700
Data Index: 5381908 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6552. Min Range: -4.6552
Max Act: 4.5927. Min Act: -0.1700
Data Index: 6270281 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6552. Min Range: -4.6552
Max Act: 4.6239. Min Act: -0.1700
Data Index: 4862295 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6552. Min Range: -4.6552
Max Act: 4.6239. Min Act: -0.1700
Data Index: 4138095 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6552. Min Range: -4.6552
Max Act: 4.6239. Min Act: -0.1700
Data Index: 3589634 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6552. Min Range: -4.6552
Max Act: 4.5927. Min Act: -0.1700
Data Index: 3019884 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6552. Min Range: -4.6552
Max Act: 4.5302. Min Act: -0.1700
Data Index: 8477572 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6552. Min Range: -4.6552
Max Act: 4.5614. Min Act: -0.1700
Data Index: 8597111 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6552. Min Range: -4.6552
Max Act: 4.5614. Min Act: -0.1700
Data Index: 1413132 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6552. Min Range: -4.6552
Max Act: 4.5614. Min Act: -0.1700
Data Index: 292120 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6552. Min Range: -4.6552
Max Act: 4.5614. Min Act: -0.1700
Data Index: 4730789 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6552. Min Range: -4.6552
Max Act: 4.5302. Min Act: -0.1699
Data Index: 5088467 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6552. Min Range: -4.6552
Max Act: 4.4989. Min Act: -0.1700
Data Index: 7861542 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6552. Min Range: -4.6552
Max Act: 4.5614. Min Act: -0.1700
Data Index: 7771592 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6552. Min Range: -4.6552
Max Act: 4.4989. Min Act: -0.1700
Data Index: 4209778 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6552. Min Range: -4.6552
Max Act: 4.4989. Min Act: -0.1700
Data Index: 7798088 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6552. Min Range: -4.6552
Max Act: 4.4989. Min Act: -0.1700
Data Index: 7664365 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6552. Min Range: -4.6552
Max Act: 4.4989. Min Act: -0.1700
Data Index: 921430 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6552. Min Range: -4.6552
Max Act: 4.4677. Min Act: -0.1700
Data Index: 6368453 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #19