Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1926 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.3168. Min Range: -11.3168
Max Act: 11.3168. Min Act: -0.1700
Data Index: 4741464 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.3168. Min Range: -11.3168
Max Act: 11.0043. Min Act: -0.1700
Data Index: 4995617 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.3168. Min Range: -11.3168
Max Act: 10.9418. Min Act: -0.1700
Data Index: 7262603 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.3168. Min Range: -11.3168
Max Act: 10.8793. Min Act: -0.1700
Data Index: 2563077 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.3168. Min Range: -11.3168
Max Act: 10.7543. Min Act: -0.1700
Data Index: 4798864 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.3168. Min Range: -11.3168
Max Act: 10.6918. Min Act: -0.1700
Data Index: 2413021 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.3168. Min Range: -11.3168
Max Act: 10.6293. Min Act: -0.1700
Data Index: 2902995 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.3168. Min Range: -11.3168
Max Act: 10.6293. Min Act: -0.1700
Data Index: 4944342 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.3168. Min Range: -11.3168
Max Act: 10.5668. Min Act: -0.1700
Data Index: 6832386 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.3168. Min Range: -11.3168
Max Act: 10.6293. Min Act: -0.1700
Data Index: 130212 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.3168. Min Range: -11.3168
Max Act: 10.5043. Min Act: -0.1700
Data Index: 4299398 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.3168. Min Range: -11.3168
Max Act: 10.5043. Min Act: -0.1700
Data Index: 7358249 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.3168. Min Range: -11.3168
Max Act: 10.5043. Min Act: -0.1700
Data Index: 3327793 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.3168. Min Range: -11.3168
Max Act: 10.5043. Min Act: -0.1700
Data Index: 5472654 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.3168. Min Range: -11.3168
Max Act: 10.5668. Min Act: -0.1700
Data Index: 5692645 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.3168. Min Range: -11.3168
Max Act: 10.4418. Min Act: -0.1700
Data Index: 5261140 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.3168. Min Range: -11.3168
Max Act: 10.4418. Min Act: -0.1700
Data Index: 7100565 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.3168. Min Range: -11.3168
Max Act: 10.4418. Min Act: -0.1700
Data Index: 2695074 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.3168. Min Range: -11.3168
Max Act: 10.4418. Min Act: -0.1700
Data Index: 1716439 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.3168. Min Range: -11.3168
Max Act: 10.5043. Min Act: -0.1700
Data Index: 1915326 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #19