Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3653 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0316. Min Range: -6.0316
Max Act: 6.0316. Min Act: -0.1700
Data Index: 6211912 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0316. Min Range: -6.0316
Max Act: 6.0316. Min Act: -0.1700
Data Index: 7655564 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0316. Min Range: -6.0316
Max Act: 5.9379. Min Act: -0.1700
Data Index: 6610440 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0316. Min Range: -6.0316
Max Act: 5.9379. Min Act: -0.1700
Data Index: 4155272 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0316. Min Range: -6.0316
Max Act: 5.8129. Min Act: -0.1700
Data Index: 2018248 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0316. Min Range: -6.0316
Max Act: 5.7504. Min Act: -0.1700
Data Index: 6421948 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0316. Min Range: -6.0316
Max Act: 5.6879. Min Act: -0.1700
Data Index: 1378752 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0316. Min Range: -6.0316
Max Act: 5.6566. Min Act: -0.1700
Data Index: 4975952 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0316. Min Range: -6.0316
Max Act: 5.6566. Min Act: -0.1700
Data Index: 5994737 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0316. Min Range: -6.0316
Max Act: 5.6254. Min Act: -0.1700
Data Index: 7989514 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0316. Min Range: -6.0316
Max Act: 5.5941. Min Act: -0.1700
Data Index: 644921 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0316. Min Range: -6.0316
Max Act: 5.6254. Min Act: -0.1700
Data Index: 2374980 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0316. Min Range: -6.0316
Max Act: 5.5941. Min Act: -0.1700
Data Index: 648645 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0316. Min Range: -6.0316
Max Act: 5.5941. Min Act: -0.1700
Data Index: 8789752 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0316. Min Range: -6.0316
Max Act: 5.5941. Min Act: -0.1700
Data Index: 4544305 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0316. Min Range: -6.0316
Max Act: 5.5941. Min Act: -0.1700
Data Index: 8516678 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0316. Min Range: -6.0316
Max Act: 5.5629. Min Act: -0.1700
Data Index: 3139072 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0316. Min Range: -6.0316
Max Act: 5.5629. Min Act: -0.1700
Data Index: 150354 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0316. Min Range: -6.0316
Max Act: 5.5629. Min Act: -0.1700
Data Index: 4624961 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0316. Min Range: -6.0316
Max Act: 5.5629. Min Act: -0.1700
Data Index: 5526189 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #19