Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3097 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.9351. Min Range: -6.9351
Max Act: 6.9351. Min Act: -0.1700
Data Index: 1587837 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9351. Min Range: -6.9351
Max Act: 6.8414. Min Act: -0.1700
Data Index: 2624783 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9351. Min Range: -6.9351
Max Act: 6.7789. Min Act: -0.1700
Data Index: 3693782 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9351. Min Range: -6.9351
Max Act: 6.7789. Min Act: -0.1700
Data Index: 1499188 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9351. Min Range: -6.9351
Max Act: 6.7476. Min Act: -0.1700
Data Index: 8424000 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9351. Min Range: -6.9351
Max Act: 6.7164. Min Act: -0.1700
Data Index: 5377868 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9351. Min Range: -6.9351
Max Act: 6.7164. Min Act: -0.1700
Data Index: 2439534 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9351. Min Range: -6.9351
Max Act: 6.7164. Min Act: -0.1700
Data Index: 5525208 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9351. Min Range: -6.9351
Max Act: 6.7164. Min Act: -0.1700
Data Index: 7449907 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9351. Min Range: -6.9351
Max Act: 6.7164. Min Act: -0.1700
Data Index: 7709209 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9351. Min Range: -6.9351
Max Act: 6.7164. Min Act: -0.1700
Data Index: 1276895 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9351. Min Range: -6.9351
Max Act: 6.6851. Min Act: -0.1700
Data Index: 3784746 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9351. Min Range: -6.9351
Max Act: 6.6851. Min Act: -0.1700
Data Index: 4619050 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9351. Min Range: -6.9351
Max Act: 6.7164. Min Act: -0.1700
Data Index: 133655 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9351. Min Range: -6.9351
Max Act: 6.6851. Min Act: -0.1700
Data Index: 3763764 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9351. Min Range: -6.9351
Max Act: 6.6851. Min Act: -0.1700
Data Index: 886742 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9351. Min Range: -6.9351
Max Act: 6.6851. Min Act: -0.1700
Data Index: 3486172 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9351. Min Range: -6.9351
Max Act: 6.6851. Min Act: -0.1700
Data Index: 906781 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9351. Min Range: -6.9351
Max Act: 6.6851. Min Act: -0.1700
Data Index: 299145 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9351. Min Range: -6.9351
Max Act: 6.6851. Min Act: -0.1700
Data Index: 7942751 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19