Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1443 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6772. Min Range: -5.6772
Max Act: 5.6772. Min Act: -0.1700
Data Index: 29617 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6772. Min Range: -5.6772
Max Act: 5.5209. Min Act: -0.1700
Data Index: 4118063 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6772. Min Range: -5.6772
Max Act: 5.5209. Min Act: -0.1700
Data Index: 8127663 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6772. Min Range: -5.6772
Max Act: 5.4897. Min Act: -0.1700
Data Index: 2270335 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6772. Min Range: -5.6772
Max Act: 5.4272. Min Act: -0.1700
Data Index: 6228933 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6772. Min Range: -5.6772
Max Act: 5.4272. Min Act: -0.1700
Data Index: 8654201 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6772. Min Range: -5.6772
Max Act: 5.4272. Min Act: -0.1700
Data Index: 4891899 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6772. Min Range: -5.6772
Max Act: 5.4272. Min Act: -0.1700
Data Index: 6581579 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6772. Min Range: -5.6772
Max Act: 5.3959. Min Act: -0.1700
Data Index: 6742247 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6772. Min Range: -5.6772
Max Act: 5.3647. Min Act: -0.1700
Data Index: 1188007 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6772. Min Range: -5.6772
Max Act: 5.3647. Min Act: -0.1700
Data Index: 3679091 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6772. Min Range: -5.6772
Max Act: 5.3647. Min Act: -0.1700
Data Index: 1984168 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6772. Min Range: -5.6772
Max Act: 5.3647. Min Act: -0.1700
Data Index: 6169961 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6772. Min Range: -5.6772
Max Act: 5.3647. Min Act: -0.1700
Data Index: 6377249 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6772. Min Range: -5.6772
Max Act: 5.3334. Min Act: -0.1700
Data Index: 1884247 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6772. Min Range: -5.6772
Max Act: 5.3647. Min Act: -0.1700
Data Index: 7265775 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6772. Min Range: -5.6772
Max Act: 5.3647. Min Act: -0.1700
Data Index: 4142875 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6772. Min Range: -5.6772
Max Act: 5.3647. Min Act: -0.1700
Data Index: 3486688 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6772. Min Range: -5.6772
Max Act: 5.3334. Min Act: -0.1700
Data Index: 3661708 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6772. Min Range: -5.6772
Max Act: 5.3022. Min Act: -0.1700
Data Index: 3003928 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #19