Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2983 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9196. Min Range: -4.9196
Max Act: 4.9196. Min Act: -0.1700
Data Index: 7855600 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9196. Min Range: -4.9196
Max Act: 4.7321. Min Act: -0.1700
Data Index: 2126915 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9196. Min Range: -4.9196
Max Act: 4.7008. Min Act: -0.1700
Data Index: 1206089 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9196. Min Range: -4.9196
Max Act: 4.6696. Min Act: -0.1700
Data Index: 7951690 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9196. Min Range: -4.9196
Max Act: 4.6696. Min Act: -0.1700
Data Index: 1784336 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9196. Min Range: -4.9196
Max Act: 4.5446. Min Act: -0.1700
Data Index: 4500622 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9196. Min Range: -4.9196
Max Act: 4.5446. Min Act: -0.1700
Data Index: 3753529 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9196. Min Range: -4.9196
Max Act: 4.5446. Min Act: -0.1700
Data Index: 3875486 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9196. Min Range: -4.9196
Max Act: 4.5133. Min Act: -0.1700
Data Index: 8593809 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9196. Min Range: -4.9196
Max Act: 4.4821. Min Act: -0.1700
Data Index: 7535409 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9196. Min Range: -4.9196
Max Act: 4.4821. Min Act: -0.1700
Data Index: 6942905 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9196. Min Range: -4.9196
Max Act: 4.4821. Min Act: -0.1700
Data Index: 7808710 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9196. Min Range: -4.9196
Max Act: 4.4821. Min Act: -0.1700
Data Index: 6389602 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9196. Min Range: -4.9196
Max Act: 4.4508. Min Act: -0.1700
Data Index: 713002 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9196. Min Range: -4.9196
Max Act: 4.4508. Min Act: -0.1700
Data Index: 8538231 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9196. Min Range: -4.9196
Max Act: 4.4508. Min Act: -0.1700
Data Index: 5891803 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9196. Min Range: -4.9196
Max Act: 4.4196. Min Act: -0.1700
Data Index: 5480913 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9196. Min Range: -4.9196
Max Act: 4.4196. Min Act: -0.1700
Data Index: 404281 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9196. Min Range: -4.9196
Max Act: 4.4196. Min Act: -0.1700
Data Index: 2639420 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9196. Min Range: -4.9196
Max Act: 4.4196. Min Act: -0.1700
Data Index: 5012655 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #19