Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 17 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9061. Min Range: -4.9061
Max Act: 4.9061. Min Act: -0.1700
Data Index: 6403833 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9061. Min Range: -4.9061
Max Act: 4.6874. Min Act: -0.1700
Data Index: 6835732 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9061. Min Range: -4.9061
Max Act: 4.6249. Min Act: -0.1700
Data Index: 1200783 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9061. Min Range: -4.9061
Max Act: 4.5936. Min Act: -0.1700
Data Index: 5857359 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9061. Min Range: -4.9061
Max Act: 4.4999. Min Act: -0.1700
Data Index: 3302922 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9061. Min Range: -4.9061
Max Act: 4.4999. Min Act: -0.1700
Data Index: 5235009 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9061. Min Range: -4.9061
Max Act: 4.4999. Min Act: -0.1700
Data Index: 854947 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9061. Min Range: -4.9061
Max Act: 4.4374. Min Act: -0.1700
Data Index: 5279142 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9061. Min Range: -4.9061
Max Act: 4.4999. Min Act: -0.1700
Data Index: 2862896 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9061. Min Range: -4.9061
Max Act: 4.4686. Min Act: -0.1700
Data Index: 8545727 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9061. Min Range: -4.9061
Max Act: 4.4374. Min Act: -0.1700
Data Index: 54243 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9061. Min Range: -4.9061
Max Act: 4.4061. Min Act: -0.1700
Data Index: 1075462 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9061. Min Range: -4.9061
Max Act: 4.4686. Min Act: -0.1700
Data Index: 2656643 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9061. Min Range: -4.9061
Max Act: 4.4374. Min Act: -0.1700
Data Index: 5904858 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9061. Min Range: -4.9061
Max Act: 4.4061. Min Act: -0.1700
Data Index: 202913 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9061. Min Range: -4.9061
Max Act: 4.4061. Min Act: -0.1700
Data Index: 5017583 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9061. Min Range: -4.9061
Max Act: 4.4061. Min Act: -0.1700
Data Index: 3082252 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9061. Min Range: -4.9061
Max Act: 4.4061. Min Act: -0.1700
Data Index: 5355467 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9061. Min Range: -4.9061
Max Act: 4.4061. Min Act: -0.1700
Data Index: 495995 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9061. Min Range: -4.9061
Max Act: 4.3749. Min Act: -0.1700
Data Index: 4397184 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #19