Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1856 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5178. Min Range: -5.5178
Max Act: 5.5178. Min Act: -0.1699
Data Index: 1115854 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5178. Min Range: -5.5178
Max Act: 5.4865. Min Act: -0.1700
Data Index: 8825904 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5178. Min Range: -5.5178
Max Act: 5.4865. Min Act: -0.1700
Data Index: 142206 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5178. Min Range: -5.5178
Max Act: 5.4865. Min Act: -0.1700
Data Index: 6009711 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5178. Min Range: -5.5178
Max Act: 5.4240. Min Act: -0.1700
Data Index: 3720478 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5178. Min Range: -5.5178
Max Act: 5.4240. Min Act: -0.1700
Data Index: 2058162 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5178. Min Range: -5.5178
Max Act: 5.4240. Min Act: -0.1700
Data Index: 5263511 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5178. Min Range: -5.5178
Max Act: 5.4553. Min Act: -0.1700
Data Index: 444573 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5178. Min Range: -5.5178
Max Act: 5.4553. Min Act: -0.1700
Data Index: 2807940 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5178. Min Range: -5.5178
Max Act: 5.4240. Min Act: -0.1700
Data Index: 320843 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5178. Min Range: -5.5178
Max Act: 5.4240. Min Act: -0.1700
Data Index: 5177645 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5178. Min Range: -5.5178
Max Act: 5.4240. Min Act: -0.1700
Data Index: 6856661 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5178. Min Range: -5.5178
Max Act: 5.3928. Min Act: -0.1700
Data Index: 8345380 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5178. Min Range: -5.5178
Max Act: 5.4240. Min Act: -0.1700
Data Index: 5151858 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5178. Min Range: -5.5178
Max Act: 5.3928. Min Act: -0.1700
Data Index: 2178694 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5178. Min Range: -5.5178
Max Act: 5.3928. Min Act: -0.1700
Data Index: 3498069 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5178. Min Range: -5.5178
Max Act: 5.3928. Min Act: -0.1700
Data Index: 6375412 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5178. Min Range: -5.5178
Max Act: 5.3928. Min Act: -0.1700
Data Index: 1566711 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5178. Min Range: -5.5178
Max Act: 5.3928. Min Act: -0.1700
Data Index: 1654023 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5178. Min Range: -5.5178
Max Act: 5.3928. Min Act: -0.1700
Data Index: 3578467 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #19