Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3474 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.8069. Min Range: -2.8069
Max Act: 2.8069. Min Act: -0.1700
Data Index: 5565605 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8069. Min Range: -2.8069
Max Act: 2.7431. Min Act: -0.1700
Data Index: 5809012 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8069. Min Range: -2.8069
Max Act: 2.6150. Min Act: -0.1700
Data Index: 1375274 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8069. Min Range: -2.8069
Max Act: 2.5989. Min Act: -0.1700
Data Index: 7003981 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8069. Min Range: -2.8069
Max Act: 2.5989. Min Act: -0.1700
Data Index: 3076918 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8069. Min Range: -2.8069
Max Act: 2.5989. Min Act: -0.1700
Data Index: 1365792 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8069. Min Range: -2.8069
Max Act: 2.5828. Min Act: -0.1700
Data Index: 1372337 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8069. Min Range: -2.8069
Max Act: 2.4858. Min Act: -0.1700
Data Index: 4491477 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8069. Min Range: -2.8069
Max Act: 2.4208. Min Act: -0.1700
Data Index: 4738987 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8069. Min Range: -2.8069
Max Act: 2.4045. Min Act: -0.1700
Data Index: 2311386 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8069. Min Range: -2.8069
Max Act: 2.3390. Min Act: -0.1700
Data Index: 4855313 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8069. Min Range: -2.8069
Max Act: 2.3390. Min Act: -0.1700
Data Index: 5460281 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8069. Min Range: -2.8069
Max Act: 2.2897. Min Act: -0.1700
Data Index: 6205960 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8069. Min Range: -2.8069
Max Act: 2.2733. Min Act: -0.1700
Data Index: 2706719 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8069. Min Range: -2.8069
Max Act: 2.2568. Min Act: -0.1700
Data Index: 5282339 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8069. Min Range: -2.8069
Max Act: 2.2568. Min Act: -0.1700
Data Index: 5438198 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8069. Min Range: -2.8069
Max Act: 2.2402. Min Act: -0.1700
Data Index: 2648834 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8069. Min Range: -2.8069
Max Act: 2.2237. Min Act: -0.1700
Data Index: 1257556 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8069. Min Range: -2.8069
Max Act: 2.2237. Min Act: -0.1700
Data Index: 598811 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8069. Min Range: -2.8069
Max Act: 2.2237. Min Act: -0.1700
Data Index: 1776480 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #19