Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5384 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6366. Min Range: -8.6366
Max Act: 8.5741. Min Act: -0.1700
Data Index: 7125232 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6366. Min Range: -8.6366
Max Act: 8.6366. Min Act: -0.1700
Data Index: 7547671 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6366. Min Range: -8.6366
Max Act: 8.4491. Min Act: -0.1700
Data Index: 1974868 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6366. Min Range: -8.6366
Max Act: 8.4491. Min Act: -0.1700
Data Index: 5631831 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6366. Min Range: -8.6366
Max Act: 8.0741. Min Act: -0.1700
Data Index: 8073837 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6366. Min Range: -8.6366
Max Act: 8.0741. Min Act: -0.1700
Data Index: 4239996 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6366. Min Range: -8.6366
Max Act: 8.0116. Min Act: -0.1700
Data Index: 2024992 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6366. Min Range: -8.6366
Max Act: 8.0116. Min Act: -0.1700
Data Index: 1059105 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6366. Min Range: -8.6366
Max Act: 7.9491. Min Act: -0.1700
Data Index: 3804789 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6366. Min Range: -8.6366
Max Act: 7.9491. Min Act: -0.1700
Data Index: 5763644 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6366. Min Range: -8.6366
Max Act: 7.9491. Min Act: -0.1700
Data Index: 3204465 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6366. Min Range: -8.6366
Max Act: 7.9491. Min Act: -0.1700
Data Index: 3786004 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6366. Min Range: -8.6366
Max Act: 7.8241. Min Act: -0.1700
Data Index: 5679141 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6366. Min Range: -8.6366
Max Act: 7.8241. Min Act: -0.1700
Data Index: 8399063 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6366. Min Range: -8.6366
Max Act: 7.8241. Min Act: -0.1700
Data Index: 5957225 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6366. Min Range: -8.6366
Max Act: 7.7616. Min Act: -0.1700
Data Index: 4617366 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6366. Min Range: -8.6366
Max Act: 7.7616. Min Act: -0.1700
Data Index: 1337391 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6366. Min Range: -8.6366
Max Act: 7.7616. Min Act: -0.1700
Data Index: 5849932 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6366. Min Range: -8.6366
Max Act: 7.7616. Min Act: -0.1700
Data Index: 7916690 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6366. Min Range: -8.6366
Max Act: 7.7303. Min Act: -0.1700
Data Index: 5036190 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #19