Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3257 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.3103. Min Range: -4.3103
Max Act: 4.3103. Min Act: -0.1700
Data Index: 3054995 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3103. Min Range: -4.3103
Max Act: 4.2477. Min Act: -0.1700
Data Index: 3054993 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3103. Min Range: -4.3103
Max Act: 4.0915. Min Act: -0.1700
Data Index: 3055011 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3103. Min Range: -4.3103
Max Act: 3.8414. Min Act: -0.1700
Data Index: 8324227 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3103. Min Range: -4.3103
Max Act: 3.8414. Min Act: -0.1700
Data Index: 2121636 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3103. Min Range: -4.3103
Max Act: 3.8414. Min Act: -0.1700
Data Index: 6331588 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3103. Min Range: -4.3103
Max Act: 3.8726. Min Act: -0.1700
Data Index: 4446112 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3103. Min Range: -4.3103
Max Act: 3.8414. Min Act: -0.1700
Data Index: 4979736 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3103. Min Range: -4.3103
Max Act: 3.8101. Min Act: -0.1700
Data Index: 2908378 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3103. Min Range: -4.3103
Max Act: 3.7788. Min Act: -0.1700
Data Index: 4767282 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3103. Min Range: -4.3103
Max Act: 3.7788. Min Act: -0.1700
Data Index: 3107269 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3103. Min Range: -4.3103
Max Act: 3.7475. Min Act: -0.1700
Data Index: 3945568 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3103. Min Range: -4.3103
Max Act: 3.7475. Min Act: -0.1700
Data Index: 6863200 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3103. Min Range: -4.3103
Max Act: 3.7475. Min Act: -0.1700
Data Index: 7075420 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3103. Min Range: -4.3103
Max Act: 3.7475. Min Act: -0.1700
Data Index: 4994441 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3103. Min Range: -4.3103
Max Act: 3.7475. Min Act: -0.1700
Data Index: 3272788 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3103. Min Range: -4.3103
Max Act: 3.7319. Min Act: -0.1700
Data Index: 4311701 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3103. Min Range: -4.3103
Max Act: 3.7475. Min Act: -0.1700
Data Index: 3770968 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3103. Min Range: -4.3103
Max Act: 3.7475. Min Act: -0.1700
Data Index: 6856653 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3103. Min Range: -4.3103
Max Act: 3.7475. Min Act: -0.1700
Data Index: 2457293 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19