Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4303 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.9207. Min Range: -4.9207
Max Act: 4.9207. Min Act: -0.1700
Data Index: 751618 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9207. Min Range: -4.9207
Max Act: 4.8895. Min Act: -0.1700
Data Index: 6895955 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9207. Min Range: -4.9207
Max Act: 4.8895. Min Act: -0.1700
Data Index: 4777583 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9207. Min Range: -4.9207
Max Act: 4.8582. Min Act: -0.1700
Data Index: 7119692 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9207. Min Range: -4.9207
Max Act: 4.8582. Min Act: -0.1700
Data Index: 4666067 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9207. Min Range: -4.9207
Max Act: 4.7957. Min Act: -0.1700
Data Index: 3712160 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9207. Min Range: -4.9207
Max Act: 4.7645. Min Act: -0.1700
Data Index: 5177061 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9207. Min Range: -4.9207
Max Act: 4.7645. Min Act: -0.1700
Data Index: 1934544 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9207. Min Range: -4.9207
Max Act: 4.7957. Min Act: -0.1700
Data Index: 2497979 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9207. Min Range: -4.9207
Max Act: 4.7332. Min Act: -0.1700
Data Index: 2176253 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9207. Min Range: -4.9207
Max Act: 4.7645. Min Act: -0.1700
Data Index: 4605925 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9207. Min Range: -4.9207
Max Act: 4.7020. Min Act: -0.1700
Data Index: 507731 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9207. Min Range: -4.9207
Max Act: 4.7332. Min Act: -0.1700
Data Index: 3371847 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9207. Min Range: -4.9207
Max Act: 4.7332. Min Act: -0.1700
Data Index: 8257701 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9207. Min Range: -4.9207
Max Act: 4.7020. Min Act: -0.1700
Data Index: 950704 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9207. Min Range: -4.9207
Max Act: 4.7020. Min Act: -0.1700
Data Index: 5267494 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9207. Min Range: -4.9207
Max Act: 4.7332. Min Act: -0.1700
Data Index: 2628321 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9207. Min Range: -4.9207
Max Act: 4.7020. Min Act: -0.1700
Data Index: 5859842 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9207. Min Range: -4.9207
Max Act: 4.7020. Min Act: -0.1700
Data Index: 3959315 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9207. Min Range: -4.9207
Max Act: 4.6707. Min Act: -0.1700
Data Index: 8252486 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #19