Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1943 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4557. Min Range: -5.4557
Max Act: 5.4557. Min Act: -0.1700
Data Index: 1696066 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4557. Min Range: -5.4557
Max Act: 5.2682. Min Act: -0.1700
Data Index: 4466928 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4557. Min Range: -5.4557
Max Act: 5.2057. Min Act: -0.1700
Data Index: 8022838 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4557. Min Range: -5.4557
Max Act: 5.1119. Min Act: -0.1700
Data Index: 1751306 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4557. Min Range: -5.4557
Max Act: 5.1119. Min Act: -0.1700
Data Index: 4403620 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4557. Min Range: -5.4557
Max Act: 5.0807. Min Act: -0.1700
Data Index: 7976687 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4557. Min Range: -5.4557
Max Act: 5.0807. Min Act: -0.1700
Data Index: 6087629 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4557. Min Range: -5.4557
Max Act: 5.0182. Min Act: -0.1700
Data Index: 1866332 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4557. Min Range: -5.4557
Max Act: 5.0494. Min Act: -0.1700
Data Index: 370203 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4557. Min Range: -5.4557
Max Act: 5.0182. Min Act: -0.1700
Data Index: 4290695 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4557. Min Range: -5.4557
Max Act: 4.9557. Min Act: -0.1700
Data Index: 3094555 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4557. Min Range: -5.4557
Max Act: 4.9557. Min Act: -0.1700
Data Index: 736725 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4557. Min Range: -5.4557
Max Act: 4.9557. Min Act: -0.1700
Data Index: 7802387 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4557. Min Range: -5.4557
Max Act: 4.9244. Min Act: -0.1700
Data Index: 2425681 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4557. Min Range: -5.4557
Max Act: 4.8932. Min Act: -0.1700
Data Index: 4686853 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4557. Min Range: -5.4557
Max Act: 4.8932. Min Act: -0.1700
Data Index: 6476912 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4557. Min Range: -5.4557
Max Act: 4.8932. Min Act: -0.1700
Data Index: 2970850 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4557. Min Range: -5.4557
Max Act: 4.8932. Min Act: -0.1700
Data Index: 7465022 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4557. Min Range: -5.4557
Max Act: 4.8307. Min Act: -0.1700
Data Index: 4275974 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4557. Min Range: -5.4557
Max Act: 4.8619. Min Act: -0.1700
Data Index: 4944448 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #19