Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 463 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5220. Min Range: -4.5220
Max Act: 4.5220. Min Act: -0.1700
Data Index: 8721513 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5220. Min Range: -4.5220
Max Act: 4.4907. Min Act: -0.1700
Data Index: 7281782 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5220. Min Range: -4.5220
Max Act: 4.4907. Min Act: -0.1700
Data Index: 4619661 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5220. Min Range: -4.5220
Max Act: 4.4595. Min Act: -0.1700
Data Index: 4676627 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5220. Min Range: -4.5220
Max Act: 4.4595. Min Act: -0.1700
Data Index: 1093191 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5220. Min Range: -4.5220
Max Act: 4.4282. Min Act: -0.1700
Data Index: 3300662 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5220. Min Range: -4.5220
Max Act: 4.4282. Min Act: -0.1700
Data Index: 6467762 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5220. Min Range: -4.5220
Max Act: 4.4282. Min Act: -0.1700
Data Index: 3247862 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5220. Min Range: -4.5220
Max Act: 4.4282. Min Act: -0.1700
Data Index: 1935826 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5220. Min Range: -4.5220
Max Act: 4.4282. Min Act: -0.1700
Data Index: 5656303 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5220. Min Range: -4.5220
Max Act: 4.4282. Min Act: -0.1700
Data Index: 1875690 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5220. Min Range: -4.5220
Max Act: 4.3970. Min Act: -0.1700
Data Index: 5102337 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5220. Min Range: -4.5220
Max Act: 4.4282. Min Act: -0.1700
Data Index: 2732430 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5220. Min Range: -4.5220
Max Act: 4.3970. Min Act: -0.1700
Data Index: 8721514 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5220. Min Range: -4.5220
Max Act: 4.4282. Min Act: -0.1700
Data Index: 276832 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5220. Min Range: -4.5220
Max Act: 4.3970. Min Act: -0.1700
Data Index: 3984546 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5220. Min Range: -4.5220
Max Act: 4.3970. Min Act: -0.1700
Data Index: 5479950 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5220. Min Range: -4.5220
Max Act: 4.3970. Min Act: -0.1700
Data Index: 5628061 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5220. Min Range: -4.5220
Max Act: 4.3970. Min Act: -0.1700
Data Index: 502999 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5220. Min Range: -4.5220
Max Act: 4.3970. Min Act: -0.1700
Data Index: 3188453 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #19