Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1546 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.7986. Min Range: -2.7986
Max Act: 2.7986. Min Act: -0.1700
Data Index: 5529477 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7986. Min Range: -2.7986
Max Act: 2.7667. Min Act: -0.1700
Data Index: 4610525 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7986. Min Range: -2.7986
Max Act: 2.7348. Min Act: -0.1700
Data Index: 1307457 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7986. Min Range: -2.7986
Max Act: 2.6868. Min Act: -0.1700
Data Index: 851189 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7986. Min Range: -2.7986
Max Act: 2.6868. Min Act: -0.1700
Data Index: 8111228 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7986. Min Range: -2.7986
Max Act: 2.6548. Min Act: -0.1700
Data Index: 334620 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7986. Min Range: -2.7986
Max Act: 2.6387. Min Act: -0.1700
Data Index: 2970128 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7986. Min Range: -2.7986
Max Act: 2.6387. Min Act: -0.1700
Data Index: 6785904 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7986. Min Range: -2.7986
Max Act: 2.6227. Min Act: -0.1700
Data Index: 3362624 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7986. Min Range: -2.7986
Max Act: 2.6387. Min Act: -0.1700
Data Index: 4993231 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7986. Min Range: -2.7986
Max Act: 2.6066. Min Act: -0.1700
Data Index: 506797 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7986. Min Range: -2.7986
Max Act: 2.6227. Min Act: -0.1700
Data Index: 2151257 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7986. Min Range: -2.7986
Max Act: 2.6227. Min Act: -0.1700
Data Index: 3728819 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7986. Min Range: -2.7986
Max Act: 2.6066. Min Act: -0.1700
Data Index: 1456976 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7986. Min Range: -2.7986
Max Act: 2.6066. Min Act: -0.1700
Data Index: 476338 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7986. Min Range: -2.7986
Max Act: 2.6066. Min Act: -0.1700
Data Index: 5662071 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7986. Min Range: -2.7986
Max Act: 2.5905. Min Act: -0.1700
Data Index: 1307456 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7986. Min Range: -2.7986
Max Act: 2.6066. Min Act: -0.1700
Data Index: 2409013 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7986. Min Range: -2.7986
Max Act: 2.5905. Min Act: -0.1700
Data Index: 4743865 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7986. Min Range: -2.7986
Max Act: 2.5905. Min Act: -0.1700
Data Index: 1966619 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #19