Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3740 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4486. Min Range: -5.4486
Max Act: 5.4486. Min Act: -0.1700
Data Index: 1344352 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4486. Min Range: -5.4486
Max Act: 5.2924. Min Act: -0.1700
Data Index: 8008532 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4486. Min Range: -5.4486
Max Act: 5.2611. Min Act: -0.1700
Data Index: 7699961 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4486. Min Range: -5.4486
Max Act: 5.2299. Min Act: -0.1700
Data Index: 229706 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4486. Min Range: -5.4486
Max Act: 5.1674. Min Act: -0.1700
Data Index: 6490787 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4486. Min Range: -5.4486
Max Act: 5.1674. Min Act: -0.1700
Data Index: 4967943 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4486. Min Range: -5.4486
Max Act: 5.1674. Min Act: -0.1700
Data Index: 7500671 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4486. Min Range: -5.4486
Max Act: 5.1361. Min Act: -0.1700
Data Index: 1298487 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4486. Min Range: -5.4486
Max Act: 5.1361. Min Act: -0.1700
Data Index: 7500670 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4486. Min Range: -5.4486
Max Act: 5.1049. Min Act: -0.1700
Data Index: 6084442 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4486. Min Range: -5.4486
Max Act: 5.1049. Min Act: -0.1700
Data Index: 3129998 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4486. Min Range: -5.4486
Max Act: 5.0736. Min Act: -0.1700
Data Index: 6862615 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4486. Min Range: -5.4486
Max Act: 5.0736. Min Act: -0.1700
Data Index: 2405221 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4486. Min Range: -5.4486
Max Act: 5.1049. Min Act: -0.1700
Data Index: 1989853 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4486. Min Range: -5.4486
Max Act: 5.0111. Min Act: -0.1700
Data Index: 8792495 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4486. Min Range: -5.4486
Max Act: 5.0424. Min Act: -0.1700
Data Index: 655939 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4486. Min Range: -5.4486
Max Act: 5.0111. Min Act: -0.1700
Data Index: 3809128 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4486. Min Range: -5.4486
Max Act: 5.0424. Min Act: -0.1700
Data Index: 2475289 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4486. Min Range: -5.4486
Max Act: 5.0111. Min Act: -0.1700
Data Index: 1049950 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4486. Min Range: -5.4486
Max Act: 5.0111. Min Act: -0.1700
Data Index: 3523996 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #19