Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 979 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.5104. Min Range: -6.5104
Max Act: 6.5104. Min Act: -0.1700
Data Index: 789501 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5104. Min Range: -6.5104
Max Act: 6.1979. Min Act: -0.1700
Data Index: 2254955 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5104. Min Range: -6.5104
Max Act: 6.1979. Min Act: -0.1700
Data Index: 7347270 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5104. Min Range: -6.5104
Max Act: 6.1979. Min Act: -0.1700
Data Index: 3276443 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5104. Min Range: -6.5104
Max Act: 6.1979. Min Act: -0.1700
Data Index: 4960649 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5104. Min Range: -6.5104
Max Act: 6.1042. Min Act: -0.1700
Data Index: 5848278 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5104. Min Range: -6.5104
Max Act: 6.1042. Min Act: -0.1700
Data Index: 23414 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5104. Min Range: -6.5104
Max Act: 6.1042. Min Act: -0.1700
Data Index: 8434606 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5104. Min Range: -6.5104
Max Act: 6.1042. Min Act: -0.1700
Data Index: 6038745 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5104. Min Range: -6.5104
Max Act: 6.0729. Min Act: -0.1700
Data Index: 6695004 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5104. Min Range: -6.5104
Max Act: 6.0729. Min Act: -0.1700
Data Index: 1852354 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5104. Min Range: -6.5104
Max Act: 6.0417. Min Act: -0.1700
Data Index: 27379 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5104. Min Range: -6.5104
Max Act: 6.0417. Min Act: -0.1700
Data Index: 2620010 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5104. Min Range: -6.5104
Max Act: 6.0104. Min Act: -0.1700
Data Index: 7434259 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5104. Min Range: -6.5104
Max Act: 5.9792. Min Act: -0.1700
Data Index: 2108473 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5104. Min Range: -6.5104
Max Act: 5.9792. Min Act: -0.1700
Data Index: 425312 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5104. Min Range: -6.5104
Max Act: 5.9479. Min Act: -0.1700
Data Index: 5061734 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5104. Min Range: -6.5104
Max Act: 6.0104. Min Act: -0.1700
Data Index: 4701964 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5104. Min Range: -6.5104
Max Act: 5.9792. Min Act: -0.1700
Data Index: 6486469 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5104. Min Range: -6.5104
Max Act: 5.9792. Min Act: -0.1700
Data Index: 7519992 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #19