Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2662 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9600. Min Range: -5.9600
Max Act: 5.9600. Min Act: -0.1700
Data Index: 950680 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9600. Min Range: -5.9600
Max Act: 5.9287. Min Act: -0.1700
Data Index: 6604178 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9600. Min Range: -5.9600
Max Act: 5.9287. Min Act: -0.1700
Data Index: 5508548 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9600. Min Range: -5.9600
Max Act: 5.8350. Min Act: -0.1700
Data Index: 93471 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9600. Min Range: -5.9600
Max Act: 5.7725. Min Act: -0.1700
Data Index: 3949741 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9600. Min Range: -5.9600
Max Act: 5.8350. Min Act: -0.1700
Data Index: 1377844 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9600. Min Range: -5.9600
Max Act: 5.8037. Min Act: -0.1700
Data Index: 5190673 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9600. Min Range: -5.9600
Max Act: 5.7725. Min Act: -0.1700
Data Index: 603752 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9600. Min Range: -5.9600
Max Act: 5.7725. Min Act: -0.1700
Data Index: 3760307 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9600. Min Range: -5.9600
Max Act: 5.8037. Min Act: -0.1700
Data Index: 7466942 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9600. Min Range: -5.9600
Max Act: 5.7100. Min Act: -0.1700
Data Index: 7462936 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9600. Min Range: -5.9600
Max Act: 5.7100. Min Act: -0.1700
Data Index: 8502277 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9600. Min Range: -5.9600
Max Act: 5.7100. Min Act: -0.1700
Data Index: 8520254 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9600. Min Range: -5.9600
Max Act: 5.6787. Min Act: -0.1700
Data Index: 211867 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9600. Min Range: -5.9600
Max Act: 5.6787. Min Act: -0.1700
Data Index: 2919006 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9600. Min Range: -5.9600
Max Act: 5.6787. Min Act: -0.1700
Data Index: 8359566 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9600. Min Range: -5.9600
Max Act: 5.6475. Min Act: -0.1700
Data Index: 5328321 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9600. Min Range: -5.9600
Max Act: 5.6162. Min Act: -0.1700
Data Index: 8319430 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9600. Min Range: -5.9600
Max Act: 5.5537. Min Act: -0.1700
Data Index: 476039 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9600. Min Range: -5.9600
Max Act: 5.5850. Min Act: -0.1700
Data Index: 6573578 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #19