Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4047 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.9546. Min Range: -4.9546
Max Act: 4.9546. Min Act: -0.1700
Data Index: 1164988 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9546. Min Range: -4.9546
Max Act: 4.9233. Min Act: -0.1699
Data Index: 8684383 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9546. Min Range: -4.9546
Max Act: 4.8296. Min Act: -0.1700
Data Index: 7513833 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9546. Min Range: -4.9546
Max Act: 4.7983. Min Act: -0.1700
Data Index: 4426355 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9546. Min Range: -4.9546
Max Act: 4.7983. Min Act: -0.1700
Data Index: 7488352 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9546. Min Range: -4.9546
Max Act: 4.7671. Min Act: -0.1700
Data Index: 5754767 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9546. Min Range: -4.9546
Max Act: 4.7358. Min Act: -0.1700
Data Index: 2818704 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9546. Min Range: -4.9546
Max Act: 4.7046. Min Act: -0.1700
Data Index: 6883050 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9546. Min Range: -4.9546
Max Act: 4.6733. Min Act: -0.1700
Data Index: 6391926 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9546. Min Range: -4.9546
Max Act: 4.6421. Min Act: -0.1700
Data Index: 6964402 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9546. Min Range: -4.9546
Max Act: 4.6108. Min Act: -0.1700
Data Index: 3624037 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9546. Min Range: -4.9546
Max Act: 4.6108. Min Act: -0.1700
Data Index: 4595227 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9546. Min Range: -4.9546
Max Act: 4.5796. Min Act: -0.1700
Data Index: 7566031 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9546. Min Range: -4.9546
Max Act: 4.5796. Min Act: -0.1700
Data Index: 4473128 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9546. Min Range: -4.9546
Max Act: 4.5796. Min Act: -0.1700
Data Index: 9324 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9546. Min Range: -4.9546
Max Act: 4.5171. Min Act: -0.1700
Data Index: 7586680 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9546. Min Range: -4.9546
Max Act: 4.5171. Min Act: -0.1700
Data Index: 5813307 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9546. Min Range: -4.9546
Max Act: 4.5171. Min Act: -0.1700
Data Index: 2391222 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9546. Min Range: -4.9546
Max Act: 4.5483. Min Act: -0.1700
Data Index: 6940838 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9546. Min Range: -4.9546
Max Act: 4.5483. Min Act: -0.1700
Data Index: 5113774 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19