Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2479 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.0788. Min Range: -5.0788
Max Act: 5.0788. Min Act: -0.1691
Data Index: 3138594 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0788. Min Range: -5.0788
Max Act: 4.9851. Min Act: -0.1700
Data Index: 5831007 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0788. Min Range: -5.0788
Max Act: 4.9226. Min Act: -0.1700
Data Index: 8645310 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0788. Min Range: -5.0788
Max Act: 4.8913. Min Act: -0.1700
Data Index: 1093083 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0788. Min Range: -5.0788
Max Act: 4.8601. Min Act: -0.1700
Data Index: 1620836 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0788. Min Range: -5.0788
Max Act: 4.8913. Min Act: -0.1700
Data Index: 2870609 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0788. Min Range: -5.0788
Max Act: 4.8288. Min Act: -0.1700
Data Index: 7178854 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0788. Min Range: -5.0788
Max Act: 4.8288. Min Act: -0.1700
Data Index: 856766 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0788. Min Range: -5.0788
Max Act: 4.7663. Min Act: -0.1700
Data Index: 8351717 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0788. Min Range: -5.0788
Max Act: 4.7663. Min Act: -0.1700
Data Index: 7279188 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0788. Min Range: -5.0788
Max Act: 4.7351. Min Act: -0.1700
Data Index: 6934408 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0788. Min Range: -5.0788
Max Act: 4.7663. Min Act: -0.1697
Data Index: 4893233 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0788. Min Range: -5.0788
Max Act: 4.7663. Min Act: -0.1700
Data Index: 3628354 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0788. Min Range: -5.0788
Max Act: 4.7976. Min Act: -0.1700
Data Index: 5908621 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0788. Min Range: -5.0788
Max Act: 4.7663. Min Act: -0.1700
Data Index: 4040677 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0788. Min Range: -5.0788
Max Act: 4.7976. Min Act: -0.1700
Data Index: 4469470 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0788. Min Range: -5.0788
Max Act: 4.7351. Min Act: -0.1700
Data Index: 7053507 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0788. Min Range: -5.0788
Max Act: 4.7038. Min Act: -0.1694
Data Index: 6597040 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0788. Min Range: -5.0788
Max Act: 4.7351. Min Act: -0.1700
Data Index: 774835 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0788. Min Range: -5.0788
Max Act: 4.7038. Min Act: -0.1700
Data Index: 6633459 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #19