Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1287 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6537. Min Range: -8.6537
Max Act: 8.6537. Min Act: -0.1700
Data Index: 2275981 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6537. Min Range: -8.6537
Max Act: 8.4662. Min Act: -0.1700
Data Index: 2944258 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6537. Min Range: -8.6537
Max Act: 8.4037. Min Act: -0.1700
Data Index: 7641829 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6537. Min Range: -8.6537
Max Act: 8.3412. Min Act: -0.1700
Data Index: 4694562 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6537. Min Range: -8.6537
Max Act: 8.3412. Min Act: -0.1700
Data Index: 4148748 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6537. Min Range: -8.6537
Max Act: 8.2162. Min Act: -0.1700
Data Index: 7601755 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6537. Min Range: -8.6537
Max Act: 8.2162. Min Act: -0.1700
Data Index: 1851602 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6537. Min Range: -8.6537
Max Act: 8.2162. Min Act: -0.1700
Data Index: 6497150 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6537. Min Range: -8.6537
Max Act: 8.1537. Min Act: -0.1700
Data Index: 3511784 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6537. Min Range: -8.6537
Max Act: 8.1537. Min Act: -0.1700
Data Index: 8749647 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6537. Min Range: -8.6537
Max Act: 8.0912. Min Act: -0.1700
Data Index: 3916595 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6537. Min Range: -8.6537
Max Act: 8.0912. Min Act: -0.1700
Data Index: 1816672 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6537. Min Range: -8.6537
Max Act: 8.0912. Min Act: -0.1700
Data Index: 8491417 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6537. Min Range: -8.6537
Max Act: 8.0912. Min Act: -0.1700
Data Index: 6906457 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6537. Min Range: -8.6537
Max Act: 8.0287. Min Act: -0.1700
Data Index: 35131 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6537. Min Range: -8.6537
Max Act: 7.9662. Min Act: -0.1700
Data Index: 5760342 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6537. Min Range: -8.6537
Max Act: 7.9037. Min Act: -0.1700
Data Index: 5874340 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6537. Min Range: -8.6537
Max Act: 7.9037. Min Act: -0.1700
Data Index: 138117 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6537. Min Range: -8.6537
Max Act: 7.9037. Min Act: -0.1700
Data Index: 59104 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6537. Min Range: -8.6537
Max Act: 7.9037. Min Act: -0.1700
Data Index: 7163142 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #19