Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.4466. Min Range: -3.4466
Max Act: 3.4309. Min Act: -0.1700
Data Index: 5019315 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4466. Min Range: -3.4466
Max Act: 3.4466. Min Act: -0.1700
Data Index: 8050594 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4466. Min Range: -3.4466
Max Act: 3.3525. Min Act: -0.1700
Data Index: 5431596 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4466. Min Range: -3.4466
Max Act: 3.2897. Min Act: -0.1700
Data Index: 3479535 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4466. Min Range: -3.4466
Max Act: 3.2740. Min Act: -0.1700
Data Index: 3025426 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4466. Min Range: -3.4466
Max Act: 3.2583. Min Act: -0.1700
Data Index: 8346480 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4466. Min Range: -3.4466
Max Act: 3.2426. Min Act: -0.1700
Data Index: 214875 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4466. Min Range: -3.4466
Max Act: 3.2426. Min Act: -0.1700
Data Index: 5772495 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4466. Min Range: -3.4466
Max Act: 3.2112. Min Act: -0.1700
Data Index: 1762112 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4466. Min Range: -3.4466
Max Act: 3.2426. Min Act: -0.1700
Data Index: 8178350 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4466. Min Range: -3.4466
Max Act: 3.2269. Min Act: -0.1700
Data Index: 5463499 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4466. Min Range: -3.4466
Max Act: 3.2269. Min Act: -0.1700
Data Index: 637415 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4466. Min Range: -3.4466
Max Act: 3.2269. Min Act: -0.1700
Data Index: 6213013 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4466. Min Range: -3.4466
Max Act: 3.2269. Min Act: -0.1700
Data Index: 5986895 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4466. Min Range: -3.4466
Max Act: 3.1640. Min Act: -0.1700
Data Index: 4852391 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4466. Min Range: -3.4466
Max Act: 3.1797. Min Act: -0.1700
Data Index: 7501918 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4466. Min Range: -3.4466
Max Act: 3.1954. Min Act: -0.1700
Data Index: 2573536 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4466. Min Range: -3.4466
Max Act: 3.1954. Min Act: -0.1700
Data Index: 7553367 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4466. Min Range: -3.4466
Max Act: 3.1640. Min Act: -0.1700
Data Index: 1459428 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4466. Min Range: -3.4466
Max Act: 3.1797. Min Act: -0.1700
Data Index: 1509233 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #19