Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3581 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.3908. Min Range: -10.3908
Max Act: 10.3908. Min Act: -0.1700
Data Index: 7849200 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.3908. Min Range: -10.3908
Max Act: 9.9533. Min Act: -0.1700
Data Index: 7919533 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.3908. Min Range: -10.3908
Max Act: 9.8283. Min Act: -0.1700
Data Index: 4502603 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.3908. Min Range: -10.3908
Max Act: 9.8283. Min Act: -0.1700
Data Index: 6359174 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.3908. Min Range: -10.3908
Max Act: 9.7033. Min Act: -0.1700
Data Index: 7676558 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.3908. Min Range: -10.3908
Max Act: 9.5783. Min Act: -0.1700
Data Index: 7418599 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.3908. Min Range: -10.3908
Max Act: 9.5158. Min Act: -0.1700
Data Index: 1112120 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.3908. Min Range: -10.3908
Max Act: 9.5783. Min Act: -0.1700
Data Index: 497011 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.3908. Min Range: -10.3908
Max Act: 9.6408. Min Act: -0.1700
Data Index: 6566650 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.3908. Min Range: -10.3908
Max Act: 9.5158. Min Act: -0.1700
Data Index: 8729253 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.3908. Min Range: -10.3908
Max Act: 9.5158. Min Act: -0.1700
Data Index: 509005 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.3908. Min Range: -10.3908
Max Act: 9.5158. Min Act: -0.1700
Data Index: 2595440 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.3908. Min Range: -10.3908
Max Act: 9.5158. Min Act: -0.1700
Data Index: 3397887 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.3908. Min Range: -10.3908
Max Act: 9.5158. Min Act: -0.1700
Data Index: 1737444 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.3908. Min Range: -10.3908
Max Act: 9.4533. Min Act: -0.1700
Data Index: 3344958 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.3908. Min Range: -10.3908
Max Act: 9.4533. Min Act: -0.1700
Data Index: 7366792 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.3908. Min Range: -10.3908
Max Act: 9.4533. Min Act: -0.1700
Data Index: 2628711 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.3908. Min Range: -10.3908
Max Act: 9.4533. Min Act: -0.1700
Data Index: 5919334 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.3908. Min Range: -10.3908
Max Act: 9.4533. Min Act: -0.1700
Data Index: 3839247 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.3908. Min Range: -10.3908
Max Act: 9.3908. Min Act: -0.1700
Data Index: 8238825 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #19