Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3413 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.5356. Min Range: -6.5356
Max Act: 6.5356. Min Act: -0.1700
Data Index: 1929935 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5356. Min Range: -6.5356
Max Act: 6.3794. Min Act: -0.1700
Data Index: 8374938 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5356. Min Range: -6.5356
Max Act: 6.2231. Min Act: -0.1700
Data Index: 2891353 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5356. Min Range: -6.5356
Max Act: 6.1606. Min Act: -0.1700
Data Index: 4970552 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5356. Min Range: -6.5356
Max Act: 6.1606. Min Act: -0.1700
Data Index: 7326378 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5356. Min Range: -6.5356
Max Act: 6.1294. Min Act: -0.1700
Data Index: 2452548 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5356. Min Range: -6.5356
Max Act: 6.0981. Min Act: -0.1700
Data Index: 7856761 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5356. Min Range: -6.5356
Max Act: 6.0981. Min Act: -0.1700
Data Index: 6315313 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5356. Min Range: -6.5356
Max Act: 6.0669. Min Act: -0.1700
Data Index: 7084969 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5356. Min Range: -6.5356
Max Act: 6.0669. Min Act: -0.1700
Data Index: 648534 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5356. Min Range: -6.5356
Max Act: 6.0356. Min Act: -0.1700
Data Index: 7831479 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5356. Min Range: -6.5356
Max Act: 5.9419. Min Act: -0.1700
Data Index: 5906394 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5356. Min Range: -6.5356
Max Act: 5.9731. Min Act: -0.1700
Data Index: 2904067 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5356. Min Range: -6.5356
Max Act: 5.9419. Min Act: -0.1700
Data Index: 7750318 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5356. Min Range: -6.5356
Max Act: 5.9106. Min Act: -0.1700
Data Index: 4838257 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5356. Min Range: -6.5356
Max Act: 5.9106. Min Act: -0.1700
Data Index: 2451515 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5356. Min Range: -6.5356
Max Act: 5.9106. Min Act: -0.1700
Data Index: 1686574 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5356. Min Range: -6.5356
Max Act: 5.9106. Min Act: -0.1700
Data Index: 1038449 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5356. Min Range: -6.5356
Max Act: 5.8794. Min Act: -0.1700
Data Index: 2481844 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5356. Min Range: -6.5356
Max Act: 5.8794. Min Act: -0.1700
Data Index: 4964737 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #19