Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1744 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.6288. Min Range: -4.6288
Max Act: 4.6288. Min Act: -0.1700
Data Index: 5693900 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6288. Min Range: -4.6288
Max Act: 4.5663. Min Act: -0.1700
Data Index: 7645611 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6288. Min Range: -4.6288
Max Act: 4.5350. Min Act: -0.1700
Data Index: 6276503 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6288. Min Range: -4.6288
Max Act: 4.5038. Min Act: -0.1700
Data Index: 8124880 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6288. Min Range: -4.6288
Max Act: 4.4413. Min Act: -0.1700
Data Index: 6770428 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6288. Min Range: -4.6288
Max Act: 4.3788. Min Act: -0.1700
Data Index: 4869800 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6288. Min Range: -4.6288
Max Act: 4.3788. Min Act: -0.1700
Data Index: 6074896 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6288. Min Range: -4.6288
Max Act: 4.3475. Min Act: -0.1700
Data Index: 6820035 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6288. Min Range: -4.6288
Max Act: 4.4100. Min Act: -0.1700
Data Index: 1180617 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6288. Min Range: -4.6288
Max Act: 4.3788. Min Act: -0.1700
Data Index: 1520449 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6288. Min Range: -4.6288
Max Act: 4.3475. Min Act: -0.1700
Data Index: 5229232 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6288. Min Range: -4.6288
Max Act: 4.3788. Min Act: -0.1700
Data Index: 3980885 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6288. Min Range: -4.6288
Max Act: 4.3163. Min Act: -0.1700
Data Index: 3656606 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6288. Min Range: -4.6288
Max Act: 4.3163. Min Act: -0.1700
Data Index: 414768 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6288. Min Range: -4.6288
Max Act: 4.2538. Min Act: -0.1700
Data Index: 6371251 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6288. Min Range: -4.6288
Max Act: 4.2538. Min Act: -0.1700
Data Index: 1499409 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6288. Min Range: -4.6288
Max Act: 4.2850. Min Act: -0.1700
Data Index: 2601121 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6288. Min Range: -4.6288
Max Act: 4.2850. Min Act: -0.1700
Data Index: 287578 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6288. Min Range: -4.6288
Max Act: 4.2850. Min Act: -0.1700
Data Index: 5494529 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6288. Min Range: -4.6288
Max Act: 4.2850. Min Act: -0.1700
Data Index: 6914165 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #19