Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 586 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.3537. Min Range: -6.3537
Max Act: 6.3537. Min Act: -0.1700
Data Index: 282445 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3537. Min Range: -6.3537
Max Act: 6.2599. Min Act: -0.1700
Data Index: 5268211 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3537. Min Range: -6.3537
Max Act: 6.1974. Min Act: -0.1700
Data Index: 2271935 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3537. Min Range: -6.3537
Max Act: 6.2287. Min Act: -0.1700
Data Index: 488076 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3537. Min Range: -6.3537
Max Act: 6.1974. Min Act: -0.1700
Data Index: 1707946 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3537. Min Range: -6.3537
Max Act: 6.1349. Min Act: -0.1700
Data Index: 1237272 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3537. Min Range: -6.3537
Max Act: 6.1349. Min Act: -0.1700
Data Index: 5633721 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3537. Min Range: -6.3537
Max Act: 6.1037. Min Act: -0.1700
Data Index: 4687846 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3537. Min Range: -6.3537
Max Act: 6.0724. Min Act: -0.1700
Data Index: 613359 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3537. Min Range: -6.3537
Max Act: 6.1349. Min Act: -0.1700
Data Index: 845538 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3537. Min Range: -6.3537
Max Act: 6.1037. Min Act: -0.1700
Data Index: 7224746 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3537. Min Range: -6.3537
Max Act: 6.1349. Min Act: -0.1700
Data Index: 695610 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3537. Min Range: -6.3537
Max Act: 6.1037. Min Act: -0.1700
Data Index: 695608 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3537. Min Range: -6.3537
Max Act: 6.0412. Min Act: -0.1700
Data Index: 7355727 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3537. Min Range: -6.3537
Max Act: 6.0412. Min Act: -0.1700
Data Index: 4049012 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3537. Min Range: -6.3537
Max Act: 6.0412. Min Act: -0.1700
Data Index: 6323622 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3537. Min Range: -6.3537
Max Act: 6.0412. Min Act: -0.1700
Data Index: 7614273 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3537. Min Range: -6.3537
Max Act: 6.0724. Min Act: -0.1700
Data Index: 2934788 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3537. Min Range: -6.3537
Max Act: 6.0099. Min Act: -0.1700
Data Index: 2488302 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3537. Min Range: -6.3537
Max Act: 6.0099. Min Act: -0.1700
Data Index: 5370943 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #19