Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2508 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.8836. Min Range: -3.8836
Max Act: 3.8836. Min Act: -0.1700
Data Index: 3354424 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8836. Min Range: -3.8836
Max Act: 3.7272. Min Act: -0.1700
Data Index: 1337942 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8836. Min Range: -3.8836
Max Act: 3.7429. Min Act: -0.1700
Data Index: 8182463 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8836. Min Range: -3.8836
Max Act: 3.6959. Min Act: -0.1700
Data Index: 5769089 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8836. Min Range: -3.8836
Max Act: 3.6803. Min Act: -0.1700
Data Index: 4120916 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8836. Min Range: -3.8836
Max Act: 3.6803. Min Act: -0.1700
Data Index: 8154461 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8836. Min Range: -3.8836
Max Act: 3.6803. Min Act: -0.1700
Data Index: 2277405 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8836. Min Range: -3.8836
Max Act: 3.6803. Min Act: -0.1700
Data Index: 940955 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8836. Min Range: -3.8836
Max Act: 3.6646. Min Act: -0.1700
Data Index: 1190391 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8836. Min Range: -3.8836
Max Act: 3.6646. Min Act: -0.1700
Data Index: 3027369 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8836. Min Range: -3.8836
Max Act: 3.6490. Min Act: -0.1700
Data Index: 8142695 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8836. Min Range: -3.8836
Max Act: 3.6490. Min Act: -0.1700
Data Index: 3491004 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8836. Min Range: -3.8836
Max Act: 3.6646. Min Act: -0.1700
Data Index: 45152 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8836. Min Range: -3.8836
Max Act: 3.6334. Min Act: -0.1700
Data Index: 1513727 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8836. Min Range: -3.8836
Max Act: 3.6334. Min Act: -0.1700
Data Index: 4639147 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8836. Min Range: -3.8836
Max Act: 3.6334. Min Act: -0.1700
Data Index: 686766 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8836. Min Range: -3.8836
Max Act: 3.6177. Min Act: -0.1700
Data Index: 6072389 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8836. Min Range: -3.8836
Max Act: 3.6177. Min Act: -0.1700
Data Index: 3995450 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8836. Min Range: -3.8836
Max Act: 3.6021. Min Act: -0.1700
Data Index: 1776677 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8836. Min Range: -3.8836
Max Act: 3.6021. Min Act: -0.1700
Data Index: 1761541 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #19