Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3872 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9274. Min Range: -6.9274
Max Act: 6.9274. Min Act: -0.1700
Data Index: 2740958 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9274. Min Range: -6.9274
Max Act: 6.8649. Min Act: -0.1700
Data Index: 134902 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9274. Min Range: -6.9274
Max Act: 6.6461. Min Act: -0.1700
Data Index: 4672124 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9274. Min Range: -6.9274
Max Act: 6.5836. Min Act: -0.1700
Data Index: 1084074 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9274. Min Range: -6.9274
Max Act: 6.5524. Min Act: -0.1700
Data Index: 3820654 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9274. Min Range: -6.9274
Max Act: 6.5211. Min Act: -0.1699
Data Index: 7261068 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9274. Min Range: -6.9274
Max Act: 6.4586. Min Act: -0.1700
Data Index: 524566 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9274. Min Range: -6.9274
Max Act: 6.4586. Min Act: -0.1700
Data Index: 652261 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9274. Min Range: -6.9274
Max Act: 6.4586. Min Act: -0.1700
Data Index: 2501229 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9274. Min Range: -6.9274
Max Act: 6.4274. Min Act: -0.1700
Data Index: 4185235 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9274. Min Range: -6.9274
Max Act: 6.4274. Min Act: -0.1700
Data Index: 7724013 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9274. Min Range: -6.9274
Max Act: 6.4274. Min Act: -0.1700
Data Index: 4177134 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9274. Min Range: -6.9274
Max Act: 6.3961. Min Act: -0.1700
Data Index: 524563 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9274. Min Range: -6.9274
Max Act: 6.3961. Min Act: -0.1700
Data Index: 5931978 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9274. Min Range: -6.9274
Max Act: 6.3961. Min Act: -0.1700
Data Index: 7280463 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9274. Min Range: -6.9274
Max Act: 6.3961. Min Act: -0.1700
Data Index: 3635888 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9274. Min Range: -6.9274
Max Act: 6.3961. Min Act: -0.1700
Data Index: 3566475 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9274. Min Range: -6.9274
Max Act: 6.3961. Min Act: -0.1700
Data Index: 8078078 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9274. Min Range: -6.9274
Max Act: 6.3961. Min Act: -0.1700
Data Index: 7774821 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9274. Min Range: -6.9274
Max Act: 6.3961. Min Act: -0.1700
Data Index: 1449302 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #19