Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5724 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4492. Min Range: -7.4492
Max Act: 7.4492. Min Act: -0.1700
Data Index: 2898256 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4492. Min Range: -7.4492
Max Act: 7.3555. Min Act: -0.1700
Data Index: 6223738 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4492. Min Range: -7.4492
Max Act: 7.2617. Min Act: -0.1700
Data Index: 2680874 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4492. Min Range: -7.4492
Max Act: 7.2617. Min Act: -0.1700
Data Index: 1852414 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4492. Min Range: -7.4492
Max Act: 7.2930. Min Act: -0.1700
Data Index: 6257913 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4492. Min Range: -7.4492
Max Act: 7.1992. Min Act: -0.1700
Data Index: 7944832 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4492. Min Range: -7.4492
Max Act: 7.2305. Min Act: -0.1700
Data Index: 1858672 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4492. Min Range: -7.4492
Max Act: 7.1367. Min Act: -0.1700
Data Index: 6083705 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4492. Min Range: -7.4492
Max Act: 7.1055. Min Act: -0.1700
Data Index: 4312320 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4492. Min Range: -7.4492
Max Act: 7.0430. Min Act: -0.1700
Data Index: 114695 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4492. Min Range: -7.4492
Max Act: 7.0742. Min Act: -0.1700
Data Index: 2172726 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4492. Min Range: -7.4492
Max Act: 7.0117. Min Act: -0.1700
Data Index: 6234201 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4492. Min Range: -7.4492
Max Act: 6.9805. Min Act: -0.1700
Data Index: 2057023 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4492. Min Range: -7.4492
Max Act: 6.8867. Min Act: -0.1700
Data Index: 474776 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4492. Min Range: -7.4492
Max Act: 6.8867. Min Act: -0.1700
Data Index: 3032399 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4492. Min Range: -7.4492
Max Act: 6.8242. Min Act: -0.1700
Data Index: 149827 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4492. Min Range: -7.4492
Max Act: 6.8242. Min Act: -0.1700
Data Index: 8048541 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4492. Min Range: -7.4492
Max Act: 6.8242. Min Act: -0.1700
Data Index: 41633 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4492. Min Range: -7.4492
Max Act: 6.7930. Min Act: -0.1700
Data Index: 5649169 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4492. Min Range: -7.4492
Max Act: 6.8242. Min Act: -0.1700
Data Index: 7887320 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #19