Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4516 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.6212. Min Range: -3.6212
Max Act: 3.6212. Min Act: -0.1700
Data Index: 8409339 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6212. Min Range: -3.6212
Max Act: 3.5586. Min Act: -0.1700
Data Index: 4222515 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6212. Min Range: -3.6212
Max Act: 3.5273. Min Act: -0.1700
Data Index: 4610581 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6212. Min Range: -3.6212
Max Act: 3.4960. Min Act: -0.1700
Data Index: 2347339 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6212. Min Range: -3.6212
Max Act: 3.4647. Min Act: -0.1700
Data Index: 1960561 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6212. Min Range: -3.6212
Max Act: 3.4176. Min Act: -0.1700
Data Index: 2063112 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6212. Min Range: -3.6212
Max Act: 3.4020. Min Act: -0.1700
Data Index: 5882770 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6212. Min Range: -3.6212
Max Act: 3.3706. Min Act: -0.1700
Data Index: 700257 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6212. Min Range: -3.6212
Max Act: 3.3549. Min Act: -0.1700
Data Index: 1055167 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6212. Min Range: -3.6212
Max Act: 3.3706. Min Act: -0.1700
Data Index: 1176914 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6212. Min Range: -3.6212
Max Act: 3.3549. Min Act: -0.1700
Data Index: 401825 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6212. Min Range: -3.6212
Max Act: 3.3706. Min Act: -0.1700
Data Index: 6720452 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6212. Min Range: -3.6212
Max Act: 3.3549. Min Act: -0.1700
Data Index: 2614343 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6212. Min Range: -3.6212
Max Act: 3.3392. Min Act: -0.1700
Data Index: 3498466 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6212. Min Range: -3.6212
Max Act: 3.3392. Min Act: -0.1700
Data Index: 7626372 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6212. Min Range: -3.6212
Max Act: 3.3392. Min Act: -0.1700
Data Index: 488763 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6212. Min Range: -3.6212
Max Act: 3.3078. Min Act: -0.1700
Data Index: 3221000 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6212. Min Range: -3.6212
Max Act: 3.3392. Min Act: -0.1700
Data Index: 5081030 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6212. Min Range: -3.6212
Max Act: 3.3235. Min Act: -0.1700
Data Index: 648533 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6212. Min Range: -3.6212
Max Act: 3.3078. Min Act: -0.1700
Data Index: 6341865 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #19