Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3000 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4834. Min Range: -6.4834
Max Act: 6.4834. Min Act: -0.1700
Data Index: 757172 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4834. Min Range: -6.4834
Max Act: 6.4209. Min Act: -0.1700
Data Index: 7502956 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4834. Min Range: -6.4834
Max Act: 6.4209. Min Act: -0.1700
Data Index: 74635 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4834. Min Range: -6.4834
Max Act: 6.3584. Min Act: -0.1700
Data Index: 7407494 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4834. Min Range: -6.4834
Max Act: 6.3272. Min Act: -0.1700
Data Index: 578125 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4834. Min Range: -6.4834
Max Act: 6.2959. Min Act: -0.1700
Data Index: 1329675 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4834. Min Range: -6.4834
Max Act: 6.2959. Min Act: -0.1700
Data Index: 6774180 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4834. Min Range: -6.4834
Max Act: 6.2647. Min Act: -0.1700
Data Index: 6774186 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4834. Min Range: -6.4834
Max Act: 6.2959. Min Act: -0.1700
Data Index: 4948681 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4834. Min Range: -6.4834
Max Act: 6.2334. Min Act: -0.1700
Data Index: 474236 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4834. Min Range: -6.4834
Max Act: 6.2334. Min Act: -0.1700
Data Index: 926419 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4834. Min Range: -6.4834
Max Act: 6.2334. Min Act: -0.1700
Data Index: 6727413 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4834. Min Range: -6.4834
Max Act: 6.2022. Min Act: -0.1700
Data Index: 3383482 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4834. Min Range: -6.4834
Max Act: 6.2022. Min Act: -0.1700
Data Index: 5960214 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4834. Min Range: -6.4834
Max Act: 6.2022. Min Act: -0.1700
Data Index: 2417331 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4834. Min Range: -6.4834
Max Act: 6.1709. Min Act: -0.1700
Data Index: 2261829 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4834. Min Range: -6.4834
Max Act: 6.2022. Min Act: -0.1700
Data Index: 2364213 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4834. Min Range: -6.4834
Max Act: 6.2022. Min Act: -0.1700
Data Index: 6774182 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4834. Min Range: -6.4834
Max Act: 6.2022. Min Act: -0.1700
Data Index: 6218400 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4834. Min Range: -6.4834
Max Act: 6.1709. Min Act: -0.1700
Data Index: 6244939 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #19