Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3453 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.6355. Min Range: -3.6355
Max Act: 3.6355. Min Act: -0.1700
Data Index: 7509938 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6355. Min Range: -3.6355
Max Act: 3.5415. Min Act: -0.1700
Data Index: 223946 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6355. Min Range: -3.6355
Max Act: 3.5259. Min Act: -0.1700
Data Index: 1096765 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6355. Min Range: -3.6355
Max Act: 3.4946. Min Act: -0.1700
Data Index: 117456 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6355. Min Range: -3.6355
Max Act: 3.4162. Min Act: -0.1700
Data Index: 7509942 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6355. Min Range: -3.6355
Max Act: 3.4476. Min Act: -0.1700
Data Index: 1456239 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6355. Min Range: -3.6355
Max Act: 3.4319. Min Act: -0.1700
Data Index: 569674 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6355. Min Range: -3.6355
Max Act: 3.4319. Min Act: -0.1700
Data Index: 5768771 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6355. Min Range: -3.6355
Max Act: 3.4162. Min Act: -0.1700
Data Index: 5768768 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6355. Min Range: -3.6355
Max Act: 3.4162. Min Act: -0.1700
Data Index: 1229762 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6355. Min Range: -3.6355
Max Act: 3.4005. Min Act: -0.1700
Data Index: 3474614 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6355. Min Range: -3.6355
Max Act: 3.3692. Min Act: -0.1700
Data Index: 8027389 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6355. Min Range: -3.6355
Max Act: 3.3849. Min Act: -0.1700
Data Index: 4489116 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6355. Min Range: -3.6355
Max Act: 3.4005. Min Act: -0.1700
Data Index: 24385 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6355. Min Range: -3.6355
Max Act: 3.3692. Min Act: -0.1700
Data Index: 5658123 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6355. Min Range: -3.6355
Max Act: 3.3692. Min Act: -0.1700
Data Index: 5055682 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6355. Min Range: -3.6355
Max Act: 3.3535. Min Act: -0.1700
Data Index: 6663453 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6355. Min Range: -3.6355
Max Act: 3.3378. Min Act: -0.1700
Data Index: 1178143 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6355. Min Range: -3.6355
Max Act: 3.3378. Min Act: -0.1700
Data Index: 2159749 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6355. Min Range: -3.6355
Max Act: 3.3535. Min Act: -0.1700
Data Index: 7935833 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #19