Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1776 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7909. Min Range: -3.7909
Max Act: 3.7909. Min Act: -0.1700
Data Index: 715051 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7909. Min Range: -3.7909
Max Act: 3.7440. Min Act: -0.1700
Data Index: 7322562 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7909. Min Range: -3.7909
Max Act: 3.7284. Min Act: -0.1700
Data Index: 3285702 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7909. Min Range: -3.7909
Max Act: 3.7284. Min Act: -0.1700
Data Index: 119290 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7909. Min Range: -3.7909
Max Act: 3.7127. Min Act: -0.1700
Data Index: 5076599 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7909. Min Range: -3.7909
Max Act: 3.6971. Min Act: -0.1700
Data Index: 3531923 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7909. Min Range: -3.7909
Max Act: 3.6814. Min Act: -0.1700
Data Index: 2028303 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7909. Min Range: -3.7909
Max Act: 3.6814. Min Act: -0.1700
Data Index: 2092936 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7909. Min Range: -3.7909
Max Act: 3.6658. Min Act: -0.1700
Data Index: 8144849 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7909. Min Range: -3.7909
Max Act: 3.6658. Min Act: -0.1700
Data Index: 7485826 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7909. Min Range: -3.7909
Max Act: 3.6345. Min Act: -0.1700
Data Index: 4965149 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7909. Min Range: -3.7909
Max Act: 3.6345. Min Act: -0.1700
Data Index: 6735101 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7909. Min Range: -3.7909
Max Act: 3.6501. Min Act: -0.1700
Data Index: 3611990 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7909. Min Range: -3.7909
Max Act: 3.6501. Min Act: -0.1700
Data Index: 3438663 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7909. Min Range: -3.7909
Max Act: 3.6345. Min Act: -0.1700
Data Index: 6434193 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7909. Min Range: -3.7909
Max Act: 3.6188. Min Act: -0.1700
Data Index: 1854053 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7909. Min Range: -3.7909
Max Act: 3.6188. Min Act: -0.1700
Data Index: 4147423 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7909. Min Range: -3.7909
Max Act: 3.6032. Min Act: -0.1700
Data Index: 8788683 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7909. Min Range: -3.7909
Max Act: 3.6032. Min Act: -0.1700
Data Index: 8556375 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7909. Min Range: -3.7909
Max Act: 3.6032. Min Act: -0.1700
Data Index: 5597618 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #19