Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 672 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.2475. Min Range: -4.2475
Max Act: 4.2475. Min Act: -0.1700
Data Index: 3334528 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2475. Min Range: -4.2475
Max Act: 4.2475. Min Act: -0.1700
Data Index: 3785950 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2475. Min Range: -4.2475
Max Act: 4.2162. Min Act: -0.1700
Data Index: 8182687 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2475. Min Range: -4.2475
Max Act: 4.2475. Min Act: -0.1700
Data Index: 3781101 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2475. Min Range: -4.2475
Max Act: 4.2475. Min Act: -0.1700
Data Index: 3679550 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2475. Min Range: -4.2475
Max Act: 4.2475. Min Act: -0.1700
Data Index: 4715128 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2475. Min Range: -4.2475
Max Act: 4.1850. Min Act: -0.1700
Data Index: 3834203 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2475. Min Range: -4.2475
Max Act: 4.2162. Min Act: -0.1700
Data Index: 374168 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2475. Min Range: -4.2475
Max Act: 4.2162. Min Act: -0.1700
Data Index: 704660 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2475. Min Range: -4.2475
Max Act: 4.2162. Min Act: -0.1700
Data Index: 6970869 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2475. Min Range: -4.2475
Max Act: 4.2162. Min Act: -0.1700
Data Index: 4056116 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2475. Min Range: -4.2475
Max Act: 4.1850. Min Act: -0.1700
Data Index: 7073425 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2475. Min Range: -4.2475
Max Act: 4.1850. Min Act: -0.1700
Data Index: 2377357 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2475. Min Range: -4.2475
Max Act: 4.2162. Min Act: -0.1700
Data Index: 1900517 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2475. Min Range: -4.2475
Max Act: 4.1537. Min Act: -0.1700
Data Index: 7592042 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2475. Min Range: -4.2475
Max Act: 4.1850. Min Act: -0.1700
Data Index: 6653810 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2475. Min Range: -4.2475
Max Act: 4.1537. Min Act: -0.1700
Data Index: 588351 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2475. Min Range: -4.2475
Max Act: 4.1224. Min Act: -0.1700
Data Index: 444695 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2475. Min Range: -4.2475
Max Act: 4.1224. Min Act: -0.1700
Data Index: 7882062 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2475. Min Range: -4.2475
Max Act: 4.1224. Min Act: -0.1700
Data Index: 4392052 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #19