Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2596 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.0421. Min Range: -8.0421
Max Act: 8.0421. Min Act: -0.1700
Data Index: 7824293 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0421. Min Range: -8.0421
Max Act: 7.9483. Min Act: -0.1700
Data Index: 8763532 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0421. Min Range: -8.0421
Max Act: 7.8858. Min Act: -0.1700
Data Index: 2498353 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0421. Min Range: -8.0421
Max Act: 7.9171. Min Act: -0.1700
Data Index: 2767649 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0421. Min Range: -8.0421
Max Act: 7.8233. Min Act: -0.1700
Data Index: 1722651 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0421. Min Range: -8.0421
Max Act: 7.7921. Min Act: -0.1700
Data Index: 8134596 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0421. Min Range: -8.0421
Max Act: 7.8233. Min Act: -0.1700
Data Index: 6425085 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0421. Min Range: -8.0421
Max Act: 7.7608. Min Act: -0.1700
Data Index: 5190382 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0421. Min Range: -8.0421
Max Act: 7.7296. Min Act: -0.1700
Data Index: 2326311 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0421. Min Range: -8.0421
Max Act: 7.7296. Min Act: -0.1700
Data Index: 725028 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0421. Min Range: -8.0421
Max Act: 7.7608. Min Act: -0.1700
Data Index: 7197384 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0421. Min Range: -8.0421
Max Act: 7.7296. Min Act: -0.1700
Data Index: 7985742 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0421. Min Range: -8.0421
Max Act: 7.6983. Min Act: -0.1700
Data Index: 7050151 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0421. Min Range: -8.0421
Max Act: 7.6671. Min Act: -0.1700
Data Index: 3407333 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0421. Min Range: -8.0421
Max Act: 7.6983. Min Act: -0.1700
Data Index: 4574018 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0421. Min Range: -8.0421
Max Act: 7.6671. Min Act: -0.1700
Data Index: 8735022 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0421. Min Range: -8.0421
Max Act: 7.6671. Min Act: -0.1700
Data Index: 7780302 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0421. Min Range: -8.0421
Max Act: 7.6671. Min Act: -0.1700
Data Index: 289396 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0421. Min Range: -8.0421
Max Act: 7.6358. Min Act: -0.1700
Data Index: 7742560 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0421. Min Range: -8.0421
Max Act: 7.6358. Min Act: -0.1700
Data Index: 1562581 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #19