Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2539 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7264. Min Range: -6.7264
Max Act: 6.7264. Min Act: -0.1700
Data Index: 4917126 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7264. Min Range: -6.7264
Max Act: 5.8514. Min Act: -0.1700
Data Index: 3414824 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7264. Min Range: -6.7264
Max Act: 5.8826. Min Act: -0.1700
Data Index: 8303332 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7264. Min Range: -6.7264
Max Act: 5.8514. Min Act: -0.1700
Data Index: 473549 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7264. Min Range: -6.7264
Max Act: 5.8514. Min Act: -0.1700
Data Index: 3479481 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7264. Min Range: -6.7264
Max Act: 5.7576. Min Act: -0.1700
Data Index: 5934655 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7264. Min Range: -6.7264
Max Act: 5.7576. Min Act: -0.1700
Data Index: 1464868 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7264. Min Range: -6.7264
Max Act: 5.7264. Min Act: -0.1700
Data Index: 5933753 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7264. Min Range: -6.7264
Max Act: 5.6639. Min Act: -0.1700
Data Index: 5154856 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7264. Min Range: -6.7264
Max Act: 5.6639. Min Act: -0.1700
Data Index: 3805718 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7264. Min Range: -6.7264
Max Act: 5.6326. Min Act: -0.1700
Data Index: 1600151 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7264. Min Range: -6.7264
Max Act: 5.6326. Min Act: -0.1700
Data Index: 2422879 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7264. Min Range: -6.7264
Max Act: 5.6014. Min Act: -0.1700
Data Index: 3843435 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7264. Min Range: -6.7264
Max Act: 5.6014. Min Act: -0.1700
Data Index: 296223 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7264. Min Range: -6.7264
Max Act: 5.6014. Min Act: -0.1700
Data Index: 689901 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7264. Min Range: -6.7264
Max Act: 5.6014. Min Act: -0.1700
Data Index: 6612951 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7264. Min Range: -6.7264
Max Act: 5.6014. Min Act: -0.1700
Data Index: 1288667 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7264. Min Range: -6.7264
Max Act: 5.5701. Min Act: -0.1700
Data Index: 3467728 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7264. Min Range: -6.7264
Max Act: 5.5701. Min Act: -0.1700
Data Index: 151538 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7264. Min Range: -6.7264
Max Act: 5.5701. Min Act: -0.1700
Data Index: 5914831 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #19