Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3087 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8265. Min Range: -5.8265
Max Act: 5.8265. Min Act: -0.1700
Data Index: 8590620 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8265. Min Range: -5.8265
Max Act: 5.6703. Min Act: -0.1700
Data Index: 2610784 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8265. Min Range: -5.8265
Max Act: 5.6390. Min Act: -0.1700
Data Index: 1644633 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8265. Min Range: -5.8265
Max Act: 5.6703. Min Act: -0.1700
Data Index: 3675168 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8265. Min Range: -5.8265
Max Act: 5.6390. Min Act: -0.1700
Data Index: 1358385 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8265. Min Range: -5.8265
Max Act: 5.6078. Min Act: -0.1700
Data Index: 1475941 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8265. Min Range: -5.8265
Max Act: 5.5453. Min Act: -0.1700
Data Index: 7018953 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8265. Min Range: -5.8265
Max Act: 5.5453. Min Act: -0.1700
Data Index: 5031502 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8265. Min Range: -5.8265
Max Act: 5.5453. Min Act: -0.1700
Data Index: 1015823 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8265. Min Range: -5.8265
Max Act: 5.5140. Min Act: -0.1700
Data Index: 1813611 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8265. Min Range: -5.8265
Max Act: 5.5140. Min Act: -0.1700
Data Index: 4647114 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8265. Min Range: -5.8265
Max Act: 5.5140. Min Act: -0.1700
Data Index: 8712886 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8265. Min Range: -5.8265
Max Act: 5.4828. Min Act: -0.1700
Data Index: 2887894 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8265. Min Range: -5.8265
Max Act: 5.4828. Min Act: -0.1700
Data Index: 3980728 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8265. Min Range: -5.8265
Max Act: 5.4515. Min Act: -0.1700
Data Index: 1862447 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8265. Min Range: -5.8265
Max Act: 5.4203. Min Act: -0.1700
Data Index: 5329782 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8265. Min Range: -5.8265
Max Act: 5.4515. Min Act: -0.1700
Data Index: 5838710 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8265. Min Range: -5.8265
Max Act: 5.4203. Min Act: -0.1700
Data Index: 6732051 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8265. Min Range: -5.8265
Max Act: 5.4515. Min Act: -0.1700
Data Index: 857715 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8265. Min Range: -5.8265
Max Act: 5.4515. Min Act: -0.1700
Data Index: 4124011 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #19