Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4824 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3408. Min Range: -7.3408
Max Act: 7.3408. Min Act: -0.1700
Data Index: 3646103 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3408. Min Range: -7.3408
Max Act: 7.1845. Min Act: -0.1700
Data Index: 4454254 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3408. Min Range: -7.3408
Max Act: 7.1533. Min Act: -0.1700
Data Index: 6188526 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3408. Min Range: -7.3408
Max Act: 7.1220. Min Act: -0.1700
Data Index: 2512203 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3408. Min Range: -7.3408
Max Act: 7.0908. Min Act: -0.1700
Data Index: 455463 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3408. Min Range: -7.3408
Max Act: 7.0283. Min Act: -0.1700
Data Index: 1474548 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3408. Min Range: -7.3408
Max Act: 6.9970. Min Act: -0.1700
Data Index: 8472710 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3408. Min Range: -7.3408
Max Act: 6.9658. Min Act: -0.1700
Data Index: 8750578 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3408. Min Range: -7.3408
Max Act: 6.9345. Min Act: -0.1700
Data Index: 4142388 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3408. Min Range: -7.3408
Max Act: 6.9658. Min Act: -0.1700
Data Index: 2512201 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3408. Min Range: -7.3408
Max Act: 6.9033. Min Act: -0.1700
Data Index: 7931866 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3408. Min Range: -7.3408
Max Act: 6.8720. Min Act: -0.1700
Data Index: 2008365 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3408. Min Range: -7.3408
Max Act: 6.9033. Min Act: -0.1700
Data Index: 4979538 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3408. Min Range: -7.3408
Max Act: 6.8720. Min Act: -0.1700
Data Index: 4142387 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3408. Min Range: -7.3408
Max Act: 6.8408. Min Act: -0.1700
Data Index: 4795533 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3408. Min Range: -7.3408
Max Act: 6.8720. Min Act: -0.1700
Data Index: 347630 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3408. Min Range: -7.3408
Max Act: 6.7783. Min Act: -0.1700
Data Index: 7194799 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3408. Min Range: -7.3408
Max Act: 6.8408. Min Act: -0.1700
Data Index: 6544771 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3408. Min Range: -7.3408
Max Act: 6.8095. Min Act: -0.1700
Data Index: 6763038 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3408. Min Range: -7.3408
Max Act: 6.7783. Min Act: -0.1700
Data Index: 5869407 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #19