Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4479 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0272. Min Range: -5.0272
Max Act: 5.0272. Min Act: -0.1700
Data Index: 631658 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0272. Min Range: -5.0272
Max Act: 4.9334. Min Act: -0.1700
Data Index: 5809422 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0272. Min Range: -5.0272
Max Act: 4.8397. Min Act: -0.1700
Data Index: 1029084 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0272. Min Range: -5.0272
Max Act: 4.8084. Min Act: -0.1700
Data Index: 3894268 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0272. Min Range: -5.0272
Max Act: 4.7459. Min Act: -0.1700
Data Index: 5847811 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0272. Min Range: -5.0272
Max Act: 4.7772. Min Act: -0.1700
Data Index: 6935129 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0272. Min Range: -5.0272
Max Act: 4.8084. Min Act: -0.1700
Data Index: 1184179 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0272. Min Range: -5.0272
Max Act: 4.7459. Min Act: -0.1700
Data Index: 3846215 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0272. Min Range: -5.0272
Max Act: 4.7459. Min Act: -0.1700
Data Index: 4443708 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0272. Min Range: -5.0272
Max Act: 4.7147. Min Act: -0.1700
Data Index: 7029202 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0272. Min Range: -5.0272
Max Act: 4.6834. Min Act: -0.1700
Data Index: 8656914 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0272. Min Range: -5.0272
Max Act: 4.6834. Min Act: -0.1700
Data Index: 7719243 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0272. Min Range: -5.0272
Max Act: 4.6522. Min Act: -0.1700
Data Index: 7447710 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0272. Min Range: -5.0272
Max Act: 4.6522. Min Act: -0.1700
Data Index: 3452491 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0272. Min Range: -5.0272
Max Act: 4.6209. Min Act: -0.1700
Data Index: 2960356 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0272. Min Range: -5.0272
Max Act: 4.6209. Min Act: -0.1700
Data Index: 727228 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0272. Min Range: -5.0272
Max Act: 4.6209. Min Act: -0.1700
Data Index: 3681974 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0272. Min Range: -5.0272
Max Act: 4.6209. Min Act: -0.1700
Data Index: 8823747 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0272. Min Range: -5.0272
Max Act: 4.6209. Min Act: -0.1700
Data Index: 2281400 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0272. Min Range: -5.0272
Max Act: 4.5584. Min Act: -0.1700
Data Index: 7499285 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #19