Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3056 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.9217. Min Range: -10.9217
Max Act: 10.9217. Min Act: -0.1700
Data Index: 6815558 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.9217. Min Range: -10.9217
Max Act: 10.8592. Min Act: -0.1700
Data Index: 2810899 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.9217. Min Range: -10.9217
Max Act: 10.7342. Min Act: -0.1700
Data Index: 1856991 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.9217. Min Range: -10.9217
Max Act: 10.4842. Min Act: -0.1700
Data Index: 8064603 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.9217. Min Range: -10.9217
Max Act: 10.4217. Min Act: -0.1700
Data Index: 826659 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.9217. Min Range: -10.9217
Max Act: 10.3592. Min Act: -0.1700
Data Index: 5717269 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.9217. Min Range: -10.9217
Max Act: 10.2967. Min Act: -0.1700
Data Index: 1856990 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.9217. Min Range: -10.9217
Max Act: 10.2342. Min Act: -0.1700
Data Index: 8675862 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.9217. Min Range: -10.9217
Max Act: 10.2342. Min Act: -0.1700
Data Index: 4504875 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.9217. Min Range: -10.9217
Max Act: 10.2342. Min Act: -0.1700
Data Index: 5129473 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.9217. Min Range: -10.9217
Max Act: 10.2967. Min Act: -0.1700
Data Index: 3573755 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.9217. Min Range: -10.9217
Max Act: 10.1717. Min Act: -0.1700
Data Index: 4312765 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.9217. Min Range: -10.9217
Max Act: 10.1717. Min Act: -0.1700
Data Index: 3744163 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.9217. Min Range: -10.9217
Max Act: 10.1717. Min Act: -0.1700
Data Index: 1251003 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.9217. Min Range: -10.9217
Max Act: 10.1092. Min Act: -0.1700
Data Index: 4270350 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.9217. Min Range: -10.9217
Max Act: 10.1092. Min Act: -0.1700
Data Index: 5235959 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.9217. Min Range: -10.9217
Max Act: 10.0467. Min Act: -0.1700
Data Index: 2783131 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.9217. Min Range: -10.9217
Max Act: 10.0467. Min Act: -0.1700
Data Index: 6619741 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.9217. Min Range: -10.9217
Max Act: 10.0467. Min Act: -0.1700
Data Index: 1126333 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.9217. Min Range: -10.9217
Max Act: 9.9842. Min Act: -0.1700
Data Index: 317615 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #19