Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3241 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1229. Min Range: -4.1229
Max Act: 4.1229. Min Act: -0.1700
Data Index: 2723914 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1229. Min Range: -4.1229
Max Act: 4.1229. Min Act: -0.1700
Data Index: 1313922 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1229. Min Range: -4.1229
Max Act: 4.0917. Min Act: -0.1700
Data Index: 6114420 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1229. Min Range: -4.1229
Max Act: 4.0292. Min Act: -0.1700
Data Index: 7590864 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1229. Min Range: -4.1229
Max Act: 3.9979. Min Act: -0.1700
Data Index: 830331 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1229. Min Range: -4.1229
Max Act: 3.9979. Min Act: -0.1700
Data Index: 3086200 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1229. Min Range: -4.1229
Max Act: 3.9667. Min Act: -0.1700
Data Index: 1885943 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1229. Min Range: -4.1229
Max Act: 3.9354. Min Act: -0.1700
Data Index: 3218252 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1229. Min Range: -4.1229
Max Act: 3.9354. Min Act: -0.1700
Data Index: 3275351 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1229. Min Range: -4.1229
Max Act: 3.9354. Min Act: -0.1700
Data Index: 8655745 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1229. Min Range: -4.1229
Max Act: 3.9354. Min Act: -0.1700
Data Index: 8655734 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1229. Min Range: -4.1229
Max Act: 3.9354. Min Act: -0.1700
Data Index: 2903424 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1229. Min Range: -4.1229
Max Act: 3.9354. Min Act: -0.1700
Data Index: 6114418 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1229. Min Range: -4.1229
Max Act: 3.9041. Min Act: -0.1700
Data Index: 4256783 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1229. Min Range: -4.1229
Max Act: 3.9041. Min Act: -0.1700
Data Index: 5718135 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1229. Min Range: -4.1229
Max Act: 3.9354. Min Act: -0.1700
Data Index: 1580556 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1229. Min Range: -4.1229
Max Act: 3.9041. Min Act: -0.1700
Data Index: 3425589 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1229. Min Range: -4.1229
Max Act: 3.9041. Min Act: -0.1700
Data Index: 1885942 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1229. Min Range: -4.1229
Max Act: 3.9041. Min Act: -0.1700
Data Index: 1926886 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1229. Min Range: -4.1229
Max Act: 3.9041. Min Act: -0.1700
Data Index: 2632529 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #19