Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3564 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.6304. Min Range: -3.6304
Max Act: 3.6304. Min Act: -0.1700
Data Index: 8687991 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6304. Min Range: -3.6304
Max Act: 3.5522. Min Act: -0.1700
Data Index: 2597847 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6304. Min Range: -3.6304
Max Act: 3.5052. Min Act: -0.1700
Data Index: 6191771 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6304. Min Range: -3.6304
Max Act: 3.4739. Min Act: -0.1700
Data Index: 7251204 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6304. Min Range: -3.6304
Max Act: 3.4582. Min Act: -0.1700
Data Index: 3899731 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6304. Min Range: -3.6304
Max Act: 3.4425. Min Act: -0.1700
Data Index: 2200139 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6304. Min Range: -3.6304
Max Act: 3.4582. Min Act: -0.1700
Data Index: 955842 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6304. Min Range: -3.6304
Max Act: 3.4582. Min Act: -0.1700
Data Index: 1432514 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6304. Min Range: -3.6304
Max Act: 3.4425. Min Act: -0.1700
Data Index: 1629309 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6304. Min Range: -3.6304
Max Act: 3.4425. Min Act: -0.1700
Data Index: 8731275 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6304. Min Range: -3.6304
Max Act: 3.4269. Min Act: -0.1700
Data Index: 2130113 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6304. Min Range: -3.6304
Max Act: 3.4269. Min Act: -0.1700
Data Index: 1023182 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6304. Min Range: -3.6304
Max Act: 3.4112. Min Act: -0.1700
Data Index: 5686256 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6304. Min Range: -3.6304
Max Act: 3.4425. Min Act: -0.1700
Data Index: 4013743 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6304. Min Range: -3.6304
Max Act: 3.4112. Min Act: -0.1700
Data Index: 2807616 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6304. Min Range: -3.6304
Max Act: 3.4112. Min Act: -0.1700
Data Index: 4294684 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6304. Min Range: -3.6304
Max Act: 3.3798. Min Act: -0.1700
Data Index: 7806445 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6304. Min Range: -3.6304
Max Act: 3.3955. Min Act: -0.1700
Data Index: 1099775 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6304. Min Range: -3.6304
Max Act: 3.3955. Min Act: -0.1700
Data Index: 3243375 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6304. Min Range: -3.6304
Max Act: 3.3798. Min Act: -0.1700
Data Index: 63700 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #19