Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2547 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9490. Min Range: -3.9490
Max Act: 3.9177. Min Act: -0.1700
Data Index: 6407561 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9490. Min Range: -3.9490
Max Act: 3.9490. Min Act: -0.1700
Data Index: 1345326 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9490. Min Range: -3.9490
Max Act: 3.9177. Min Act: -0.1700
Data Index: 2825680 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9490. Min Range: -3.9490
Max Act: 3.9177. Min Act: -0.1700
Data Index: 7264629 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9490. Min Range: -3.9490
Max Act: 3.8552. Min Act: -0.1700
Data Index: 5781262 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9490. Min Range: -3.9490
Max Act: 3.8552. Min Act: -0.1700
Data Index: 4800461 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9490. Min Range: -3.9490
Max Act: 3.7770. Min Act: -0.1700
Data Index: 7081880 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9490. Min Range: -3.9490
Max Act: 3.7927. Min Act: -0.1700
Data Index: 1798307 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9490. Min Range: -3.9490
Max Act: 3.7770. Min Act: -0.1700
Data Index: 4151281 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9490. Min Range: -3.9490
Max Act: 3.7614. Min Act: -0.1700
Data Index: 5948610 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9490. Min Range: -3.9490
Max Act: 3.7614. Min Act: -0.1700
Data Index: 4581205 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9490. Min Range: -3.9490
Max Act: 3.7614. Min Act: -0.1700
Data Index: 8324128 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9490. Min Range: -3.9490
Max Act: 3.7614. Min Act: -0.1700
Data Index: 932828 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9490. Min Range: -3.9490
Max Act: 3.7457. Min Act: -0.1700
Data Index: 5300297 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9490. Min Range: -3.9490
Max Act: 3.7457. Min Act: -0.1700
Data Index: 4328156 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9490. Min Range: -3.9490
Max Act: 3.7614. Min Act: -0.1700
Data Index: 6317595 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9490. Min Range: -3.9490
Max Act: 3.7145. Min Act: -0.1700
Data Index: 8407080 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9490. Min Range: -3.9490
Max Act: 3.7301. Min Act: -0.1700
Data Index: 261321 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9490. Min Range: -3.9490
Max Act: 3.7145. Min Act: -0.1700
Data Index: 3824838 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9490. Min Range: -3.9490
Max Act: 3.7145. Min Act: -0.1700
Data Index: 3097192 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #19