Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4882 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.5196. Min Range: -11.5196
Max Act: 11.5196. Min Act: -0.1700
Data Index: 8326568 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.5196. Min Range: -11.5196
Max Act: 11.3946. Min Act: -0.1700
Data Index: 1500517 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.5196. Min Range: -11.5196
Max Act: 11.4571. Min Act: -0.1700
Data Index: 4890163 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.5196. Min Range: -11.5196
Max Act: 11.3321. Min Act: -0.1700
Data Index: 6934886 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.5196. Min Range: -11.5196
Max Act: 11.2071. Min Act: -0.1700
Data Index: 1125032 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.5196. Min Range: -11.5196
Max Act: 11.0821. Min Act: -0.1700
Data Index: 2594459 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.5196. Min Range: -11.5196
Max Act: 10.8946. Min Act: -0.1700
Data Index: 7414560 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.5196. Min Range: -11.5196
Max Act: 10.8321. Min Act: -0.1700
Data Index: 8336481 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.5196. Min Range: -11.5196
Max Act: 10.8321. Min Act: -0.1700
Data Index: 3940722 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.5196. Min Range: -11.5196
Max Act: 10.7696. Min Act: -0.1700
Data Index: 4628899 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.5196. Min Range: -11.5196
Max Act: 10.7071. Min Act: -0.1700
Data Index: 5179213 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.5196. Min Range: -11.5196
Max Act: 10.7696. Min Act: -0.1700
Data Index: 449091 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.5196. Min Range: -11.5196
Max Act: 10.8321. Min Act: -0.1700
Data Index: 5023914 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.5196. Min Range: -11.5196
Max Act: 10.7696. Min Act: -0.1700
Data Index: 4657812 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.5196. Min Range: -11.5196
Max Act: 10.7696. Min Act: -0.1700
Data Index: 2861105 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.5196. Min Range: -11.5196
Max Act: 10.7696. Min Act: -0.1700
Data Index: 8745703 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.5196. Min Range: -11.5196
Max Act: 10.7071. Min Act: -0.1700
Data Index: 7312114 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.5196. Min Range: -11.5196
Max Act: 10.7071. Min Act: -0.1700
Data Index: 7896233 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.5196. Min Range: -11.5196
Max Act: 10.6446. Min Act: -0.1700
Data Index: 2055420 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.5196. Min Range: -11.5196
Max Act: 10.7071. Min Act: -0.1700
Data Index: 5241961 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #19