Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3418 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5942. Min Range: -4.5942
Max Act: 4.5942. Min Act: -0.1700
Data Index: 8640886 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5942. Min Range: -4.5942
Max Act: 4.5317. Min Act: -0.1700
Data Index: 4898881 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5942. Min Range: -4.5942
Max Act: 4.4692. Min Act: -0.1700
Data Index: 4532073 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5942. Min Range: -4.5942
Max Act: 4.3442. Min Act: -0.1700
Data Index: 4483232 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5942. Min Range: -4.5942
Max Act: 4.3442. Min Act: -0.1700
Data Index: 2855554 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5942. Min Range: -4.5942
Max Act: 4.3442. Min Act: -0.1700
Data Index: 8737076 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5942. Min Range: -4.5942
Max Act: 4.3130. Min Act: -0.1700
Data Index: 2132210 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5942. Min Range: -4.5942
Max Act: 4.2817. Min Act: -0.1700
Data Index: 4342533 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5942. Min Range: -4.5942
Max Act: 4.2817. Min Act: -0.1700
Data Index: 2571094 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5942. Min Range: -4.5942
Max Act: 4.2504. Min Act: -0.1700
Data Index: 6318943 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5942. Min Range: -4.5942
Max Act: 4.2192. Min Act: -0.1700
Data Index: 2910483 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5942. Min Range: -4.5942
Max Act: 4.2192. Min Act: -0.1700
Data Index: 8648538 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5942. Min Range: -4.5942
Max Act: 4.2504. Min Act: -0.1700
Data Index: 6400572 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5942. Min Range: -4.5942
Max Act: 4.2192. Min Act: -0.1700
Data Index: 8080775 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5942. Min Range: -4.5942
Max Act: 4.2192. Min Act: -0.1700
Data Index: 2214611 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5942. Min Range: -4.5942
Max Act: 4.1879. Min Act: -0.1700
Data Index: 7551996 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5942. Min Range: -4.5942
Max Act: 4.1879. Min Act: -0.1700
Data Index: 516960 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5942. Min Range: -4.5942
Max Act: 4.1567. Min Act: -0.1700
Data Index: 2984085 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5942. Min Range: -4.5942
Max Act: 4.1567. Min Act: -0.1700
Data Index: 8524432 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5942. Min Range: -4.5942
Max Act: 4.1254. Min Act: -0.1700
Data Index: 6537678 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #19