Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3750 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.0903. Min Range: -4.0903
Max Act: 4.0903. Min Act: -0.1700
Data Index: 6104141 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0903. Min Range: -4.0903
Max Act: 3.9966. Min Act: -0.1700
Data Index: 4795 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0903. Min Range: -4.0903
Max Act: 3.9966. Min Act: -0.1700
Data Index: 7478101 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0903. Min Range: -4.0903
Max Act: 3.9966. Min Act: -0.1700
Data Index: 7491824 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0903. Min Range: -4.0903
Max Act: 3.9653. Min Act: -0.1700
Data Index: 2569239 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0903. Min Range: -4.0903
Max Act: 3.9653. Min Act: -0.1700
Data Index: 1625861 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0903. Min Range: -4.0903
Max Act: 3.9340. Min Act: -0.1700
Data Index: 3642675 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0903. Min Range: -4.0903
Max Act: 3.9028. Min Act: -0.1700
Data Index: 2192522 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0903. Min Range: -4.0903
Max Act: 3.8715. Min Act: -0.1700
Data Index: 5196804 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0903. Min Range: -4.0903
Max Act: 3.8715. Min Act: -0.1700
Data Index: 2215809 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0903. Min Range: -4.0903
Max Act: 3.8715. Min Act: -0.1700
Data Index: 7543966 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0903. Min Range: -4.0903
Max Act: 3.8402. Min Act: -0.1700
Data Index: 6619819 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0903. Min Range: -4.0903
Max Act: 3.8715. Min Act: -0.1700
Data Index: 5570136 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0903. Min Range: -4.0903
Max Act: 3.8402. Min Act: -0.1700
Data Index: 4170329 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0903. Min Range: -4.0903
Max Act: 3.8402. Min Act: -0.1700
Data Index: 3903437 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0903. Min Range: -4.0903
Max Act: 3.8402. Min Act: -0.1700
Data Index: 7050933 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0903. Min Range: -4.0903
Max Act: 3.8090. Min Act: -0.1700
Data Index: 5756910 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0903. Min Range: -4.0903
Max Act: 3.7777. Min Act: -0.1700
Data Index: 1604810 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0903. Min Range: -4.0903
Max Act: 3.8090. Min Act: -0.1700
Data Index: 8490552 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0903. Min Range: -4.0903
Max Act: 3.7777. Min Act: -0.1700
Data Index: 4781645 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #19