Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3767 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.8630. Min Range: -4.8630
Max Act: 4.8630. Min Act: -0.1700
Data Index: 8414724 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8630. Min Range: -4.8630
Max Act: 4.8317. Min Act: -0.1700
Data Index: 7429649 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8630. Min Range: -4.8630
Max Act: 4.6442. Min Act: -0.1700
Data Index: 7871223 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8630. Min Range: -4.8630
Max Act: 4.6442. Min Act: -0.1700
Data Index: 3938599 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8630. Min Range: -4.8630
Max Act: 4.6442. Min Act: -0.1700
Data Index: 5598880 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8630. Min Range: -4.8630
Max Act: 4.6130. Min Act: -0.1700
Data Index: 1056818 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8630. Min Range: -4.8630
Max Act: 4.6130. Min Act: -0.1700
Data Index: 8332685 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8630. Min Range: -4.8630
Max Act: 4.6130. Min Act: -0.1700
Data Index: 8652080 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8630. Min Range: -4.8630
Max Act: 4.6130. Min Act: -0.1700
Data Index: 8663565 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8630. Min Range: -4.8630
Max Act: 4.5817. Min Act: -0.1700
Data Index: 603654 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8630. Min Range: -4.8630
Max Act: 4.6130. Min Act: -0.1700
Data Index: 21469 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8630. Min Range: -4.8630
Max Act: 4.5817. Min Act: -0.1700
Data Index: 8030974 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8630. Min Range: -4.8630
Max Act: 4.5817. Min Act: -0.1700
Data Index: 4853277 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8630. Min Range: -4.8630
Max Act: 4.5817. Min Act: -0.1700
Data Index: 4888643 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8630. Min Range: -4.8630
Max Act: 4.5817. Min Act: -0.1700
Data Index: 5967680 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8630. Min Range: -4.8630
Max Act: 4.6130. Min Act: -0.1700
Data Index: 6591346 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8630. Min Range: -4.8630
Max Act: 4.5817. Min Act: -0.1700
Data Index: 3815 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8630. Min Range: -4.8630
Max Act: 4.5817. Min Act: -0.1700
Data Index: 7440496 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8630. Min Range: -4.8630
Max Act: 4.5817. Min Act: -0.1700
Data Index: 3000947 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8630. Min Range: -4.8630
Max Act: 4.5505. Min Act: -0.1700
Data Index: 5438054 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #19