Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4270 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.9960. Min Range: -4.9960
Max Act: 4.9960. Min Act: -0.1700
Data Index: 1556408 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9960. Min Range: -4.9960
Max Act: 4.9022. Min Act: -0.1700
Data Index: 8427391 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9960. Min Range: -4.9960
Max Act: 4.8085. Min Act: -0.1700
Data Index: 5257392 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9960. Min Range: -4.9960
Max Act: 4.5585. Min Act: -0.1700
Data Index: 3840348 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9960. Min Range: -4.9960
Max Act: 4.4647. Min Act: -0.1700
Data Index: 4082471 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9960. Min Range: -4.9960
Max Act: 4.4960. Min Act: -0.1700
Data Index: 2903702 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9960. Min Range: -4.9960
Max Act: 4.4335. Min Act: -0.1700
Data Index: 6039193 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9960. Min Range: -4.9960
Max Act: 4.4335. Min Act: -0.1700
Data Index: 619634 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9960. Min Range: -4.9960
Max Act: 4.3709. Min Act: -0.1700
Data Index: 807205 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9960. Min Range: -4.9960
Max Act: 4.4022. Min Act: -0.1700
Data Index: 6481583 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9960. Min Range: -4.9960
Max Act: 4.4022. Min Act: -0.1700
Data Index: 1144917 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9960. Min Range: -4.9960
Max Act: 4.4022. Min Act: -0.1700
Data Index: 2586111 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9960. Min Range: -4.9960
Max Act: 4.3709. Min Act: -0.1700
Data Index: 848052 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9960. Min Range: -4.9960
Max Act: 4.3397. Min Act: -0.1700
Data Index: 5952162 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9960. Min Range: -4.9960
Max Act: 4.3397. Min Act: -0.1700
Data Index: 522327 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9960. Min Range: -4.9960
Max Act: 4.3709. Min Act: -0.1700
Data Index: 1281449 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9960. Min Range: -4.9960
Max Act: 4.3397. Min Act: -0.1700
Data Index: 5389052 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9960. Min Range: -4.9960
Max Act: 4.3397. Min Act: -0.1700
Data Index: 90984 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9960. Min Range: -4.9960
Max Act: 4.3397. Min Act: -0.1700
Data Index: 6139866 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9960. Min Range: -4.9960
Max Act: 4.3084. Min Act: -0.1700
Data Index: 6185067 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #19