Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2898 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5133. Min Range: -5.5133
Max Act: 5.5133. Min Act: -0.1700
Data Index: 3248363 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5133. Min Range: -5.5133
Max Act: 4.8570. Min Act: -0.1700
Data Index: 3234674 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5133. Min Range: -5.5133
Max Act: 4.8258. Min Act: -0.1700
Data Index: 6480808 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5133. Min Range: -5.5133
Max Act: 4.7320. Min Act: -0.1700
Data Index: 2257331 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5133. Min Range: -5.5133
Max Act: 4.7320. Min Act: -0.1700
Data Index: 4814343 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5133. Min Range: -5.5133
Max Act: 4.7008. Min Act: -0.1700
Data Index: 2016400 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5133. Min Range: -5.5133
Max Act: 4.6695. Min Act: -0.1700
Data Index: 8183631 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5133. Min Range: -5.5133
Max Act: 4.6695. Min Act: -0.1700
Data Index: 7488479 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5133. Min Range: -5.5133
Max Act: 4.6383. Min Act: -0.1700
Data Index: 7270346 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5133. Min Range: -5.5133
Max Act: 4.6070. Min Act: -0.1700
Data Index: 2171395 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5133. Min Range: -5.5133
Max Act: 4.5758. Min Act: -0.1700
Data Index: 3053373 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5133. Min Range: -5.5133
Max Act: 4.5445. Min Act: -0.1700
Data Index: 3342796 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5133. Min Range: -5.5133
Max Act: 4.5445. Min Act: -0.1700
Data Index: 7741321 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5133. Min Range: -5.5133
Max Act: 4.5445. Min Act: -0.1700
Data Index: 3060032 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5133. Min Range: -5.5133
Max Act: 4.5133. Min Act: -0.1700
Data Index: 6685259 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5133. Min Range: -5.5133
Max Act: 4.5133. Min Act: -0.1700
Data Index: 8607404 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5133. Min Range: -5.5133
Max Act: 4.5133. Min Act: -0.1700
Data Index: 7014278 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5133. Min Range: -5.5133
Max Act: 4.5133. Min Act: -0.1700
Data Index: 1567579 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5133. Min Range: -5.5133
Max Act: 4.4820. Min Act: -0.1700
Data Index: 7302530 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5133. Min Range: -5.5133
Max Act: 4.4508. Min Act: -0.1700
Data Index: 28664 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #19