Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3236 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.1485. Min Range: -3.1485
Max Act: 3.1485. Min Act: -0.1700
Data Index: 8489758 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1485. Min Range: -3.1485
Max Act: 3.0539. Min Act: -0.1700
Data Index: 5893060 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1485. Min Range: -3.1485
Max Act: 3.0381. Min Act: -0.1700
Data Index: 3028558 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1485. Min Range: -3.1485
Max Act: 3.0065. Min Act: -0.1700
Data Index: 136882 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1485. Min Range: -3.1485
Max Act: 2.9907. Min Act: -0.1700
Data Index: 8203916 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1485. Min Range: -3.1485
Max Act: 2.9749. Min Act: -0.1700
Data Index: 1770130 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1485. Min Range: -3.1485
Max Act: 2.9907. Min Act: -0.1700
Data Index: 2593396 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1485. Min Range: -3.1485
Max Act: 2.9274. Min Act: -0.1700
Data Index: 1051200 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1485. Min Range: -3.1485
Max Act: 2.9591. Min Act: -0.1700
Data Index: 6101317 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1485. Min Range: -3.1485
Max Act: 2.9591. Min Act: -0.1700
Data Index: 485429 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1485. Min Range: -3.1485
Max Act: 2.9591. Min Act: -0.1700
Data Index: 5845366 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1485. Min Range: -3.1485
Max Act: 2.9591. Min Act: -0.1700
Data Index: 6755976 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1485. Min Range: -3.1485
Max Act: 2.9433. Min Act: -0.1700
Data Index: 1441889 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1485. Min Range: -3.1485
Max Act: 2.9433. Min Act: -0.1700
Data Index: 2391658 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1485. Min Range: -3.1485
Max Act: 2.9433. Min Act: -0.1700
Data Index: 1191289 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1485. Min Range: -3.1485
Max Act: 2.9274. Min Act: -0.1700
Data Index: 937027 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1485. Min Range: -3.1485
Max Act: 2.9274. Min Act: -0.1700
Data Index: 3733208 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1485. Min Range: -3.1485
Max Act: 2.9116. Min Act: -0.1700
Data Index: 7551079 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1485. Min Range: -3.1485
Max Act: 2.8957. Min Act: -0.1700
Data Index: 6823641 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1485. Min Range: -3.1485
Max Act: 2.9116. Min Act: -0.1700
Data Index: 4307238 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #19