Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2655 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.4349. Min Range: -3.4349
Max Act: 3.4349. Min Act: -0.1700
Data Index: 8171195 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4349. Min Range: -3.4349
Max Act: 3.2309. Min Act: -0.1700
Data Index: 2537408 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4349. Min Range: -3.4349
Max Act: 3.1995. Min Act: -0.1700
Data Index: 6473992 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4349. Min Range: -3.4349
Max Act: 3.1523. Min Act: -0.1700
Data Index: 1858786 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4349. Min Range: -3.4349
Max Act: 3.1365. Min Act: -0.1700
Data Index: 458169 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4349. Min Range: -3.4349
Max Act: 3.0735. Min Act: -0.1700
Data Index: 5395423 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4349. Min Range: -3.4349
Max Act: 3.0735. Min Act: -0.1700
Data Index: 6152151 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4349. Min Range: -3.4349
Max Act: 3.0262. Min Act: -0.1700
Data Index: 1272975 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4349. Min Range: -3.4349
Max Act: 3.0104. Min Act: -0.1700
Data Index: 8541473 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4349. Min Range: -3.4349
Max Act: 3.0104. Min Act: -0.1700
Data Index: 1740703 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4349. Min Range: -3.4349
Max Act: 3.0104. Min Act: -0.1700
Data Index: 4178927 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4349. Min Range: -3.4349
Max Act: 3.0104. Min Act: -0.1700
Data Index: 5938555 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4349. Min Range: -3.4349
Max Act: 3.0104. Min Act: -0.1700
Data Index: 944131 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4349. Min Range: -3.4349
Max Act: 2.9787. Min Act: -0.1700
Data Index: 8438722 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4349. Min Range: -3.4349
Max Act: 2.9946. Min Act: -0.1700
Data Index: 3556828 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4349. Min Range: -3.4349
Max Act: 2.9787. Min Act: -0.1700
Data Index: 5069908 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4349. Min Range: -3.4349
Max Act: 2.9946. Min Act: -0.1700
Data Index: 5644859 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4349. Min Range: -3.4349
Max Act: 2.9629. Min Act: -0.1700
Data Index: 2535904 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4349. Min Range: -3.4349
Max Act: 2.9629. Min Act: -0.1700
Data Index: 4952790 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4349. Min Range: -3.4349
Max Act: 2.9787. Min Act: -0.1700
Data Index: 2277709 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #19