Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1942 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.8181. Min Range: -2.8181
Max Act: 2.8181. Min Act: -0.1700
Data Index: 4584918 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8181. Min Range: -2.8181
Max Act: 2.8022. Min Act: -0.1700
Data Index: 163152 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8181. Min Range: -2.8181
Max Act: 2.7704. Min Act: -0.1700
Data Index: 5201312 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8181. Min Range: -2.8181
Max Act: 2.7704. Min Act: -0.1700
Data Index: 349853 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8181. Min Range: -2.8181
Max Act: 2.7863. Min Act: -0.1700
Data Index: 7056857 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8181. Min Range: -2.8181
Max Act: 2.7863. Min Act: -0.1700
Data Index: 5891117 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8181. Min Range: -2.8181
Max Act: 2.7863. Min Act: -0.1700
Data Index: 3154174 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8181. Min Range: -2.8181
Max Act: 2.7704. Min Act: -0.1700
Data Index: 6665254 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8181. Min Range: -2.8181
Max Act: 2.7225. Min Act: -0.1700
Data Index: 3779605 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8181. Min Range: -2.8181
Max Act: 2.7544. Min Act: -0.1700
Data Index: 7731765 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8181. Min Range: -2.8181
Max Act: 2.7544. Min Act: -0.1700
Data Index: 590426 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8181. Min Range: -2.8181
Max Act: 2.7544. Min Act: -0.1700
Data Index: 614582 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8181. Min Range: -2.8181
Max Act: 2.7384. Min Act: -0.1700
Data Index: 259037 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8181. Min Range: -2.8181
Max Act: 2.7225. Min Act: -0.1700
Data Index: 7437470 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8181. Min Range: -2.8181
Max Act: 2.7544. Min Act: -0.1700
Data Index: 8262919 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8181. Min Range: -2.8181
Max Act: 2.7704. Min Act: -0.1700
Data Index: 201136 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8181. Min Range: -2.8181
Max Act: 2.7225. Min Act: -0.1700
Data Index: 4627558 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8181. Min Range: -2.8181
Max Act: 2.7384. Min Act: -0.1700
Data Index: 7072655 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8181. Min Range: -2.8181
Max Act: 2.7065. Min Act: -0.1700
Data Index: 1011694 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8181. Min Range: -2.8181
Max Act: 2.7225. Min Act: -0.1700
Data Index: 5033430 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #19