Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1681 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5155. Min Range: -5.5155
Max Act: 5.5155. Min Act: -0.1700
Data Index: 1320874 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5155. Min Range: -5.5155
Max Act: 5.5155. Min Act: -0.1700
Data Index: 6078913 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5155. Min Range: -5.5155
Max Act: 5.4843. Min Act: -0.1700
Data Index: 5980614 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5155. Min Range: -5.5155
Max Act: 5.4530. Min Act: -0.1699
Data Index: 1240024 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5155. Min Range: -5.5155
Max Act: 5.4218. Min Act: -0.1700
Data Index: 8342220 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5155. Min Range: -5.5155
Max Act: 5.4218. Min Act: -0.1700
Data Index: 4476443 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5155. Min Range: -5.5155
Max Act: 5.2968. Min Act: -0.1700
Data Index: 7890023 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5155. Min Range: -5.5155
Max Act: 5.2968. Min Act: -0.1700
Data Index: 1056111 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5155. Min Range: -5.5155
Max Act: 5.3280. Min Act: -0.1700
Data Index: 6407172 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5155. Min Range: -5.5155
Max Act: 5.2343. Min Act: -0.1700
Data Index: 3879376 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5155. Min Range: -5.5155
Max Act: 5.2030. Min Act: -0.1700
Data Index: 1090561 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5155. Min Range: -5.5155
Max Act: 5.2343. Min Act: -0.1700
Data Index: 8118326 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5155. Min Range: -5.5155
Max Act: 5.1718. Min Act: -0.1700
Data Index: 2909261 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5155. Min Range: -5.5155
Max Act: 5.1405. Min Act: -0.1700
Data Index: 7182284 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5155. Min Range: -5.5155
Max Act: 5.1718. Min Act: -0.1700
Data Index: 2516225 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5155. Min Range: -5.5155
Max Act: 5.1405. Min Act: -0.1700
Data Index: 5209879 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5155. Min Range: -5.5155
Max Act: 5.1093. Min Act: -0.1700
Data Index: 6328587 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5155. Min Range: -5.5155
Max Act: 5.1405. Min Act: -0.1700
Data Index: 1936618 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5155. Min Range: -5.5155
Max Act: 5.1405. Min Act: -0.1700
Data Index: 7242532 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5155. Min Range: -5.5155
Max Act: 5.1405. Min Act: -0.1700
Data Index: 3870768 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #19