Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3596 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8334. Min Range: -6.8334
Max Act: 6.8334. Min Act: -0.1700
Data Index: 2840537 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8334. Min Range: -6.8334
Max Act: 6.7084. Min Act: -0.1700
Data Index: 1825966 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8334. Min Range: -6.8334
Max Act: 6.5209. Min Act: -0.1700
Data Index: 2688822 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8334. Min Range: -6.8334
Max Act: 6.4896. Min Act: -0.1700
Data Index: 3600600 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8334. Min Range: -6.8334
Max Act: 6.4271. Min Act: -0.1700
Data Index: 870900 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8334. Min Range: -6.8334
Max Act: 6.4271. Min Act: -0.1700
Data Index: 3624150 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8334. Min Range: -6.8334
Max Act: 6.3646. Min Act: -0.1700
Data Index: 7914411 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8334. Min Range: -6.8334
Max Act: 6.3021. Min Act: -0.1700
Data Index: 775165 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8334. Min Range: -6.8334
Max Act: 6.2709. Min Act: -0.1700
Data Index: 4224578 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8334. Min Range: -6.8334
Max Act: 6.3334. Min Act: -0.1700
Data Index: 2285616 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8334. Min Range: -6.8334
Max Act: 6.2709. Min Act: -0.1700
Data Index: 3764280 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8334. Min Range: -6.8334
Max Act: 6.2396. Min Act: -0.1700
Data Index: 7522809 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8334. Min Range: -6.8334
Max Act: 6.2396. Min Act: -0.1700
Data Index: 4274134 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8334. Min Range: -6.8334
Max Act: 6.1771. Min Act: -0.1700
Data Index: 7148431 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8334. Min Range: -6.8334
Max Act: 6.1771. Min Act: -0.1700
Data Index: 7221740 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8334. Min Range: -6.8334
Max Act: 6.1771. Min Act: -0.1700
Data Index: 3013284 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8334. Min Range: -6.8334
Max Act: 6.1771. Min Act: -0.1700
Data Index: 180990 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8334. Min Range: -6.8334
Max Act: 6.1771. Min Act: -0.1700
Data Index: 2497490 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8334. Min Range: -6.8334
Max Act: 6.1459. Min Act: -0.1700
Data Index: 4420285 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8334. Min Range: -6.8334
Max Act: 6.1459. Min Act: -0.1700
Data Index: 3549132 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #19