Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 17 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.0895. Min Range: -2.0895
Max Act: 2.0895. Min Act: -0.1700
Data Index: 2029659 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.0895. Min Range: -2.0895
Max Act: 2.0895. Min Act: -0.1699
Data Index: 2288193 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.0895. Min Range: -2.0895
Max Act: 2.0727. Min Act: -0.1700
Data Index: 4438880 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.0895. Min Range: -2.0895
Max Act: 2.0727. Min Act: -0.1700
Data Index: 121874 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.0895. Min Range: -2.0895
Max Act: 2.0222. Min Act: -0.1700
Data Index: 7921689 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.0895. Min Range: -2.0895
Max Act: 2.0222. Min Act: -0.1700
Data Index: 6698590 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.0895. Min Range: -2.0895
Max Act: 2.0391. Min Act: -0.1700
Data Index: 7042398 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.0895. Min Range: -2.0895
Max Act: 2.0222. Min Act: -0.1700
Data Index: 7703835 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.0895. Min Range: -2.0895
Max Act: 2.0222. Min Act: -0.1700
Data Index: 6388617 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.0895. Min Range: -2.0895
Max Act: 2.0222. Min Act: -0.1700
Data Index: 4877181 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.0895. Min Range: -2.0895
Max Act: 2.0053. Min Act: -0.1700
Data Index: 3380569 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.0895. Min Range: -2.0895
Max Act: 1.9884. Min Act: -0.1700
Data Index: 2693678 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.0895. Min Range: -2.0895
Max Act: 2.0053. Min Act: -0.1700
Data Index: 7322806 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.0895. Min Range: -2.0895
Max Act: 2.0053. Min Act: -0.1700
Data Index: 2713692 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.0895. Min Range: -2.0895
Max Act: 1.9715. Min Act: -0.1700
Data Index: 189807 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.0895. Min Range: -2.0895
Max Act: 2.0053. Min Act: -0.1700
Data Index: 7008510 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.0895. Min Range: -2.0895
Max Act: 2.0053. Min Act: -0.1700
Data Index: 7382401 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.0895. Min Range: -2.0895
Max Act: 1.9884. Min Act: -0.1700
Data Index: 559809 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.0895. Min Range: -2.0895
Max Act: 1.9884. Min Act: -0.1700
Data Index: 1619034 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.0895. Min Range: -2.0895
Max Act: 1.9884. Min Act: -0.1700
Data Index: 2024692 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #19