Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4420 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1438. Min Range: -5.1438
Max Act: 5.1438. Min Act: -0.1700
Data Index: 5848453 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1438. Min Range: -5.1438
Max Act: 5.1125. Min Act: -0.1700
Data Index: 1658855 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1438. Min Range: -5.1438
Max Act: 5.0813. Min Act: -0.1700
Data Index: 7030892 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1438. Min Range: -5.1438
Max Act: 5.0813. Min Act: -0.1700
Data Index: 2408120 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1438. Min Range: -5.1438
Max Act: 5.0813. Min Act: -0.1700
Data Index: 4585747 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1438. Min Range: -5.1438
Max Act: 5.0813. Min Act: -0.1700
Data Index: 3533112 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1438. Min Range: -5.1438
Max Act: 5.0500. Min Act: -0.1700
Data Index: 2343219 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1438. Min Range: -5.1438
Max Act: 5.0500. Min Act: -0.1700
Data Index: 5463982 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1438. Min Range: -5.1438
Max Act: 5.0500. Min Act: -0.1700
Data Index: 5131655 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1438. Min Range: -5.1438
Max Act: 5.0188. Min Act: -0.1700
Data Index: 2568136 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1438. Min Range: -5.1438
Max Act: 5.0188. Min Act: -0.1700
Data Index: 5030192 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1438. Min Range: -5.1438
Max Act: 4.9875. Min Act: -0.1700
Data Index: 4041738 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1438. Min Range: -5.1438
Max Act: 4.9875. Min Act: -0.1700
Data Index: 163100 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1438. Min Range: -5.1438
Max Act: 5.0188. Min Act: -0.1700
Data Index: 7840655 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1438. Min Range: -5.1438
Max Act: 4.9563. Min Act: -0.1700
Data Index: 6070439 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1438. Min Range: -5.1438
Max Act: 4.9250. Min Act: -0.1700
Data Index: 4568160 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1438. Min Range: -5.1438
Max Act: 4.9250. Min Act: -0.1700
Data Index: 7162291 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1438. Min Range: -5.1438
Max Act: 4.8938. Min Act: -0.1700
Data Index: 1338286 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1438. Min Range: -5.1438
Max Act: 4.8938. Min Act: -0.1700
Data Index: 3911019 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1438. Min Range: -5.1438
Max Act: 4.8938. Min Act: -0.1700
Data Index: 4486541 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #19