Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 323 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7227. Min Range: -5.7227
Max Act: 5.7227. Min Act: -0.1700
Data Index: 1969555 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7227. Min Range: -5.7227
Max Act: 5.6915. Min Act: -0.1700
Data Index: 793394 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7227. Min Range: -5.7227
Max Act: 5.6290. Min Act: -0.1700
Data Index: 1106402 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7227. Min Range: -5.7227
Max Act: 5.5665. Min Act: -0.1700
Data Index: 621766 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7227. Min Range: -5.7227
Max Act: 5.5977. Min Act: -0.1700
Data Index: 5400823 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7227. Min Range: -5.7227
Max Act: 5.5352. Min Act: -0.1700
Data Index: 3723521 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7227. Min Range: -5.7227
Max Act: 5.5352. Min Act: -0.1700
Data Index: 4687653 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7227. Min Range: -5.7227
Max Act: 5.5352. Min Act: -0.1700
Data Index: 6377912 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7227. Min Range: -5.7227
Max Act: 5.5040. Min Act: -0.1700
Data Index: 6841550 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7227. Min Range: -5.7227
Max Act: 5.5040. Min Act: -0.1700
Data Index: 2059685 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7227. Min Range: -5.7227
Max Act: 5.4727. Min Act: -0.1700
Data Index: 1757256 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7227. Min Range: -5.7227
Max Act: 5.4415. Min Act: -0.1700
Data Index: 3418034 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7227. Min Range: -5.7227
Max Act: 5.4415. Min Act: -0.1700
Data Index: 5545767 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7227. Min Range: -5.7227
Max Act: 5.4415. Min Act: -0.1700
Data Index: 294543 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7227. Min Range: -5.7227
Max Act: 5.4415. Min Act: -0.1700
Data Index: 8231248 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7227. Min Range: -5.7227
Max Act: 5.4102. Min Act: -0.1700
Data Index: 2735427 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7227. Min Range: -5.7227
Max Act: 5.4415. Min Act: -0.1700
Data Index: 1969286 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7227. Min Range: -5.7227
Max Act: 5.4102. Min Act: -0.1700
Data Index: 424363 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7227. Min Range: -5.7227
Max Act: 5.4102. Min Act: -0.1700
Data Index: 2553098 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7227. Min Range: -5.7227
Max Act: 5.3790. Min Act: -0.1700
Data Index: 3199860 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #19