Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 5107 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.4333. Min Range: -6.4333
Max Act: 6.4333. Min Act: -0.1700
Data Index: 2112707 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4333. Min Range: -6.4333
Max Act: 6.4333. Min Act: -0.1700
Data Index: 6606890 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4333. Min Range: -6.4333
Max Act: 6.2770. Min Act: -0.1700
Data Index: 1487681 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4333. Min Range: -6.4333
Max Act: 6.2458. Min Act: -0.1700
Data Index: 3773294 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4333. Min Range: -6.4333
Max Act: 6.2145. Min Act: -0.1700
Data Index: 3624398 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4333. Min Range: -6.4333
Max Act: 6.2145. Min Act: -0.1700
Data Index: 1152160 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4333. Min Range: -6.4333
Max Act: 6.2145. Min Act: -0.1700
Data Index: 1487670 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4333. Min Range: -6.4333
Max Act: 6.1833. Min Act: -0.1700
Data Index: 8573486 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4333. Min Range: -6.4333
Max Act: 6.1520. Min Act: -0.1700
Data Index: 3303996 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4333. Min Range: -6.4333
Max Act: 6.1833. Min Act: -0.1700
Data Index: 862867 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4333. Min Range: -6.4333
Max Act: 6.1520. Min Act: -0.1700
Data Index: 1192866 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4333. Min Range: -6.4333
Max Act: 6.1520. Min Act: -0.1700
Data Index: 1487675 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4333. Min Range: -6.4333
Max Act: 6.0895. Min Act: -0.1700
Data Index: 939541 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4333. Min Range: -6.4333
Max Act: 6.1208. Min Act: -0.1700
Data Index: 7346490 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4333. Min Range: -6.4333
Max Act: 6.0895. Min Act: -0.1700
Data Index: 2147337 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4333. Min Range: -6.4333
Max Act: 6.0895. Min Act: -0.1700
Data Index: 4962857 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4333. Min Range: -6.4333
Max Act: 6.0895. Min Act: -0.1700
Data Index: 777580 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4333. Min Range: -6.4333
Max Act: 6.0895. Min Act: -0.1700
Data Index: 4308075 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4333. Min Range: -6.4333
Max Act: 6.0895. Min Act: -0.1700
Data Index: 4048560 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4333. Min Range: -6.4333
Max Act: 6.0895. Min Act: -0.1700
Data Index: 3290916 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #19