Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2618 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7738. Min Range: -5.7738
Max Act: 5.7738. Min Act: -0.1699
Data Index: 7441542 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7738. Min Range: -5.7738
Max Act: 5.7738. Min Act: -0.1700
Data Index: 2072368 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7738. Min Range: -5.7738
Max Act: 5.6801. Min Act: -0.1700
Data Index: 6369371 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7738. Min Range: -5.7738
Max Act: 5.7113. Min Act: -0.1700
Data Index: 2638079 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7738. Min Range: -5.7738
Max Act: 5.7113. Min Act: -0.1700
Data Index: 2070299 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7738. Min Range: -5.7738
Max Act: 5.7113. Min Act: -0.1700
Data Index: 7227350 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7738. Min Range: -5.7738
Max Act: 5.6801. Min Act: -0.1700
Data Index: 3845936 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7738. Min Range: -5.7738
Max Act: 5.6176. Min Act: -0.1700
Data Index: 765880 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7738. Min Range: -5.7738
Max Act: 5.6176. Min Act: -0.1700
Data Index: 3597729 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7738. Min Range: -5.7738
Max Act: 5.5863. Min Act: -0.1700
Data Index: 5239015 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7738. Min Range: -5.7738
Max Act: 5.5551. Min Act: -0.1699
Data Index: 420383 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7738. Min Range: -5.7738
Max Act: 5.5551. Min Act: -0.1700
Data Index: 1607043 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7738. Min Range: -5.7738
Max Act: 5.5863. Min Act: -0.1700
Data Index: 3125023 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7738. Min Range: -5.7738
Max Act: 5.5238. Min Act: -0.1700
Data Index: 6548125 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7738. Min Range: -5.7738
Max Act: 5.5238. Min Act: -0.1700
Data Index: 2982965 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7738. Min Range: -5.7738
Max Act: 5.5238. Min Act: -0.1700
Data Index: 4834874 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7738. Min Range: -5.7738
Max Act: 5.4926. Min Act: -0.1700
Data Index: 7022050 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7738. Min Range: -5.7738
Max Act: 5.4613. Min Act: -0.1700
Data Index: 5128035 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7738. Min Range: -5.7738
Max Act: 5.4613. Min Act: -0.1700
Data Index: 847858 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7738. Min Range: -5.7738
Max Act: 5.4301. Min Act: -0.1700
Data Index: 5773936 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #19