Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 840 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8644. Min Range: -7.8644
Max Act: 7.8644. Min Act: -0.1700
Data Index: 4328355 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8644. Min Range: -7.8644
Max Act: 7.7394. Min Act: -0.1700
Data Index: 6410075 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8644. Min Range: -7.8644
Max Act: 7.5519. Min Act: -0.1700
Data Index: 1584574 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8644. Min Range: -7.8644
Max Act: 7.4894. Min Act: -0.1700
Data Index: 5787233 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8644. Min Range: -7.8644
Max Act: 7.4894. Min Act: -0.1700
Data Index: 8464980 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8644. Min Range: -7.8644
Max Act: 7.4894. Min Act: -0.1700
Data Index: 8360651 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8644. Min Range: -7.8644
Max Act: 7.4582. Min Act: -0.1700
Data Index: 4925162 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8644. Min Range: -7.8644
Max Act: 7.3957. Min Act: -0.1700
Data Index: 4210285 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8644. Min Range: -7.8644
Max Act: 7.3957. Min Act: -0.1700
Data Index: 3397197 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8644. Min Range: -7.8644
Max Act: 7.3957. Min Act: -0.1700
Data Index: 7130411 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8644. Min Range: -7.8644
Max Act: 7.3332. Min Act: -0.1700
Data Index: 118146 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8644. Min Range: -7.8644
Max Act: 7.3332. Min Act: -0.1700
Data Index: 8242904 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8644. Min Range: -7.8644
Max Act: 7.3332. Min Act: -0.1700
Data Index: 8405004 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8644. Min Range: -7.8644
Max Act: 7.2394. Min Act: -0.1700
Data Index: 3479347 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8644. Min Range: -7.8644
Max Act: 7.2082. Min Act: -0.1700
Data Index: 4300056 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8644. Min Range: -7.8644
Max Act: 7.1769. Min Act: -0.1700
Data Index: 2300643 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8644. Min Range: -7.8644
Max Act: 7.2082. Min Act: -0.1700
Data Index: 8552018 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8644. Min Range: -7.8644
Max Act: 7.1769. Min Act: -0.1700
Data Index: 4129697 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8644. Min Range: -7.8644
Max Act: 7.1457. Min Act: -0.1700
Data Index: 3145235 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8644. Min Range: -7.8644
Max Act: 7.1769. Min Act: -0.1700
Data Index: 7810631 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #19