Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2228 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 10.3676. Min Range: -10.3676
Max Act: 10.3676. Min Act: -0.1700
Data Index: 7236329 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.3676. Min Range: -10.3676
Max Act: 10.1176. Min Act: -0.1700
Data Index: 6903339 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.3676. Min Range: -10.3676
Max Act: 10.1801. Min Act: -0.1700
Data Index: 2823675 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.3676. Min Range: -10.3676
Max Act: 10.1176. Min Act: -0.1700
Data Index: 5701608 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.3676. Min Range: -10.3676
Max Act: 10.1176. Min Act: -0.1700
Data Index: 4430630 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.3676. Min Range: -10.3676
Max Act: 10.0551. Min Act: -0.1700
Data Index: 6206394 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.3676. Min Range: -10.3676
Max Act: 9.9301. Min Act: -0.1700
Data Index: 5804211 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.3676. Min Range: -10.3676
Max Act: 9.9926. Min Act: -0.1700
Data Index: 5978534 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.3676. Min Range: -10.3676
Max Act: 9.9926. Min Act: -0.1700
Data Index: 8661567 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.3676. Min Range: -10.3676
Max Act: 9.9926. Min Act: -0.1700
Data Index: 5062770 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.3676. Min Range: -10.3676
Max Act: 9.9926. Min Act: -0.1700
Data Index: 3307675 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.3676. Min Range: -10.3676
Max Act: 9.9301. Min Act: -0.1700
Data Index: 5673778 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.3676. Min Range: -10.3676
Max Act: 9.9301. Min Act: -0.1700
Data Index: 6015406 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.3676. Min Range: -10.3676
Max Act: 9.9301. Min Act: -0.1700
Data Index: 6370091 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.3676. Min Range: -10.3676
Max Act: 9.8676. Min Act: -0.1700
Data Index: 5169546 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.3676. Min Range: -10.3676
Max Act: 9.8676. Min Act: -0.1700
Data Index: 3518493 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.3676. Min Range: -10.3676
Max Act: 9.8051. Min Act: -0.1700
Data Index: 5575148 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.3676. Min Range: -10.3676
Max Act: 9.8051. Min Act: -0.1700
Data Index: 702053 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.3676. Min Range: -10.3676
Max Act: 9.7426. Min Act: -0.1700
Data Index: 2759888 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.3676. Min Range: -10.3676
Max Act: 9.8051. Min Act: -0.1700
Data Index: 7066772 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #19