Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1987 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5114. Min Range: -5.5114
Max Act: 5.5114. Min Act: -0.1700
Data Index: 4127008 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5114. Min Range: -5.5114
Max Act: 5.4802. Min Act: -0.1700
Data Index: 6645664 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5114. Min Range: -5.5114
Max Act: 5.2302. Min Act: -0.1700
Data Index: 367835 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5114. Min Range: -5.5114
Max Act: 5.2302. Min Act: -0.1700
Data Index: 505053 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5114. Min Range: -5.5114
Max Act: 5.2302. Min Act: -0.1700
Data Index: 4643063 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5114. Min Range: -5.5114
Max Act: 5.1364. Min Act: -0.1700
Data Index: 3519558 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5114. Min Range: -5.5114
Max Act: 5.1364. Min Act: -0.1700
Data Index: 5740259 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5114. Min Range: -5.5114
Max Act: 5.1364. Min Act: -0.1700
Data Index: 2226720 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5114. Min Range: -5.5114
Max Act: 5.1364. Min Act: -0.1700
Data Index: 8133658 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5114. Min Range: -5.5114
Max Act: 5.1052. Min Act: -0.1700
Data Index: 6645665 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5114. Min Range: -5.5114
Max Act: 5.1052. Min Act: -0.1700
Data Index: 1588372 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5114. Min Range: -5.5114
Max Act: 5.1052. Min Act: -0.1700
Data Index: 7853190 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5114. Min Range: -5.5114
Max Act: 5.0739. Min Act: -0.1700
Data Index: 6169673 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5114. Min Range: -5.5114
Max Act: 5.0739. Min Act: -0.1700
Data Index: 6029019 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5114. Min Range: -5.5114
Max Act: 5.0114. Min Act: -0.1700
Data Index: 3446652 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5114. Min Range: -5.5114
Max Act: 5.0427. Min Act: -0.1700
Data Index: 1967217 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5114. Min Range: -5.5114
Max Act: 5.0739. Min Act: -0.1700
Data Index: 3838033 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5114. Min Range: -5.5114
Max Act: 5.0427. Min Act: -0.1700
Data Index: 4704645 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5114. Min Range: -5.5114
Max Act: 5.0427. Min Act: -0.1700
Data Index: 278747 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5114. Min Range: -5.5114
Max Act: 4.9802. Min Act: -0.1700
Data Index: 216471 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #19