Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4588 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 9.3037. Min Range: -9.3037
Max Act: 9.3037. Min Act: -0.1700
Data Index: 1944805 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.3037. Min Range: -9.3037
Max Act: 9.0537. Min Act: -0.1700
Data Index: 8770677 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.3037. Min Range: -9.3037
Max Act: 8.6787. Min Act: -0.1700
Data Index: 466053 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.3037. Min Range: -9.3037
Max Act: 8.6162. Min Act: -0.1700
Data Index: 2201424 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.3037. Min Range: -9.3037
Max Act: 8.6162. Min Act: -0.1700
Data Index: 4966331 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.3037. Min Range: -9.3037
Max Act: 8.5537. Min Act: -0.1700
Data Index: 8209301 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.3037. Min Range: -9.3037
Max Act: 8.5537. Min Act: -0.1700
Data Index: 4935429 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.3037. Min Range: -9.3037
Max Act: 8.5537. Min Act: -0.1700
Data Index: 4062412 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.3037. Min Range: -9.3037
Max Act: 8.4287. Min Act: -0.1700
Data Index: 1004607 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.3037. Min Range: -9.3037
Max Act: 8.4287. Min Act: -0.1700
Data Index: 5604025 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.3037. Min Range: -9.3037
Max Act: 8.4287. Min Act: -0.1700
Data Index: 1119807 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.3037. Min Range: -9.3037
Max Act: 8.4287. Min Act: -0.1700
Data Index: 3875698 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.3037. Min Range: -9.3037
Max Act: 8.3662. Min Act: -0.1700
Data Index: 1906899 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.3037. Min Range: -9.3037
Max Act: 8.3662. Min Act: -0.1700
Data Index: 333004 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.3037. Min Range: -9.3037
Max Act: 8.3037. Min Act: -0.1700
Data Index: 7274708 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.3037. Min Range: -9.3037
Max Act: 8.2412. Min Act: -0.1700
Data Index: 3053791 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.3037. Min Range: -9.3037
Max Act: 8.3037. Min Act: -0.1700
Data Index: 4507079 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.3037. Min Range: -9.3037
Max Act: 8.2412. Min Act: -0.1700
Data Index: 6258320 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.3037. Min Range: -9.3037
Max Act: 8.2412. Min Act: -0.1700
Data Index: 3902258 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.3037. Min Range: -9.3037
Max Act: 8.2412. Min Act: -0.1700
Data Index: 3245501 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #19