Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3960 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1459. Min Range: -6.1459
Max Act: 6.1459. Min Act: -0.1700
Data Index: 2158663 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1459. Min Range: -6.1459
Max Act: 6.1147. Min Act: -0.1700
Data Index: 4645375 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1459. Min Range: -6.1459
Max Act: 6.1147. Min Act: -0.1700
Data Index: 600979 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1459. Min Range: -6.1459
Max Act: 5.9584. Min Act: -0.1700
Data Index: 775990 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1459. Min Range: -6.1459
Max Act: 5.8022. Min Act: -0.1700
Data Index: 6579696 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1459. Min Range: -6.1459
Max Act: 5.7397. Min Act: -0.1700
Data Index: 1526908 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1459. Min Range: -6.1459
Max Act: 5.7397. Min Act: -0.1700
Data Index: 1033778 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1459. Min Range: -6.1459
Max Act: 5.7397. Min Act: -0.1700
Data Index: 664409 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1459. Min Range: -6.1459
Max Act: 5.7397. Min Act: -0.1700
Data Index: 4652334 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1459. Min Range: -6.1459
Max Act: 5.6772. Min Act: -0.1700
Data Index: 7815771 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1459. Min Range: -6.1459
Max Act: 5.6772. Min Act: -0.1700
Data Index: 6819119 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1459. Min Range: -6.1459
Max Act: 5.7084. Min Act: -0.1700
Data Index: 4897020 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1459. Min Range: -6.1459
Max Act: 5.6459. Min Act: -0.1700
Data Index: 4576768 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1459. Min Range: -6.1459
Max Act: 5.6147. Min Act: -0.1700
Data Index: 2281547 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1459. Min Range: -6.1459
Max Act: 5.5834. Min Act: -0.1700
Data Index: 1116576 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1459. Min Range: -6.1459
Max Act: 5.6147. Min Act: -0.1700
Data Index: 5187056 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1459. Min Range: -6.1459
Max Act: 5.5834. Min Act: -0.1700
Data Index: 5985754 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1459. Min Range: -6.1459
Max Act: 5.5834. Min Act: -0.1700
Data Index: 49085 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1459. Min Range: -6.1459
Max Act: 5.5834. Min Act: -0.1700
Data Index: 1358036 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1459. Min Range: -6.1459
Max Act: 5.5522. Min Act: -0.1700
Data Index: 2862623 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #19