Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 787 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2527. Min Range: -6.2527
Max Act: 6.2527. Min Act: -0.1700
Data Index: 5212262 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2527. Min Range: -6.2527
Max Act: 6.2527. Min Act: -0.1700
Data Index: 29537 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2527. Min Range: -6.2527
Max Act: 6.2215. Min Act: -0.1700
Data Index: 6334619 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2527. Min Range: -6.2527
Max Act: 6.1590. Min Act: -0.1700
Data Index: 8271434 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2527. Min Range: -6.2527
Max Act: 6.1590. Min Act: -0.1700
Data Index: 145634 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2527. Min Range: -6.2527
Max Act: 6.1277. Min Act: -0.1700
Data Index: 769596 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2527. Min Range: -6.2527
Max Act: 6.1277. Min Act: -0.1700
Data Index: 8765326 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2527. Min Range: -6.2527
Max Act: 6.0965. Min Act: -0.1700
Data Index: 603968 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2527. Min Range: -6.2527
Max Act: 6.0965. Min Act: -0.1700
Data Index: 4798917 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2527. Min Range: -6.2527
Max Act: 6.0027. Min Act: -0.1700
Data Index: 2056352 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2527. Min Range: -6.2527
Max Act: 5.9715. Min Act: -0.1700
Data Index: 3336150 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2527. Min Range: -6.2527
Max Act: 5.9090. Min Act: -0.1700
Data Index: 6726474 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2527. Min Range: -6.2527
Max Act: 5.9715. Min Act: -0.1700
Data Index: 89043 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2527. Min Range: -6.2527
Max Act: 5.9402. Min Act: -0.1700
Data Index: 2941089 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2527. Min Range: -6.2527
Max Act: 5.9090. Min Act: -0.1700
Data Index: 1990701 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2527. Min Range: -6.2527
Max Act: 5.8777. Min Act: -0.1700
Data Index: 1324679 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2527. Min Range: -6.2527
Max Act: 5.8777. Min Act: -0.1700
Data Index: 1853507 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2527. Min Range: -6.2527
Max Act: 5.8777. Min Act: -0.1700
Data Index: 3807007 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2527. Min Range: -6.2527
Max Act: 5.9090. Min Act: -0.1700
Data Index: 5415815 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2527. Min Range: -6.2527
Max Act: 5.8465. Min Act: -0.1700
Data Index: 8122744 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #19