Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3004 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4002. Min Range: -6.4002
Max Act: 6.4002. Min Act: -0.1700
Data Index: 5470175 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4002. Min Range: -6.4002
Max Act: 6.3377. Min Act: -0.1700
Data Index: 5045536 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4002. Min Range: -6.4002
Max Act: 6.3689. Min Act: -0.1700
Data Index: 8429830 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4002. Min Range: -6.4002
Max Act: 6.3377. Min Act: -0.1700
Data Index: 5604305 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4002. Min Range: -6.4002
Max Act: 6.3377. Min Act: -0.1700
Data Index: 4344013 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4002. Min Range: -6.4002
Max Act: 6.2752. Min Act: -0.1700
Data Index: 8092054 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4002. Min Range: -6.4002
Max Act: 6.2439. Min Act: -0.1700
Data Index: 6066194 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4002. Min Range: -6.4002
Max Act: 6.2127. Min Act: -0.1700
Data Index: 1479663 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4002. Min Range: -6.4002
Max Act: 6.2439. Min Act: -0.1700
Data Index: 5373774 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4002. Min Range: -6.4002
Max Act: 6.1502. Min Act: -0.1700
Data Index: 8660656 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4002. Min Range: -6.4002
Max Act: 6.1502. Min Act: -0.1700
Data Index: 4700563 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4002. Min Range: -6.4002
Max Act: 6.1814. Min Act: -0.1700
Data Index: 4269685 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4002. Min Range: -6.4002
Max Act: 6.1502. Min Act: -0.1700
Data Index: 1904195 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4002. Min Range: -6.4002
Max Act: 6.1502. Min Act: -0.1700
Data Index: 3763832 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4002. Min Range: -6.4002
Max Act: 6.1502. Min Act: -0.1700
Data Index: 7510492 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4002. Min Range: -6.4002
Max Act: 6.1814. Min Act: -0.1700
Data Index: 4982390 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4002. Min Range: -6.4002
Max Act: 6.1189. Min Act: -0.1700
Data Index: 4446852 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4002. Min Range: -6.4002
Max Act: 6.1189. Min Act: -0.1700
Data Index: 4763180 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4002. Min Range: -6.4002
Max Act: 6.0877. Min Act: -0.1700
Data Index: 590923 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4002. Min Range: -6.4002
Max Act: 6.1189. Min Act: -0.1700
Data Index: 530104 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #19