Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 579 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.3663. Min Range: -8.3663
Max Act: 8.3663. Min Act: -0.1700
Data Index: 4257897 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3663. Min Range: -8.3663
Max Act: 8.3038. Min Act: -0.1700
Data Index: 6830074 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3663. Min Range: -8.3663
Max Act: 8.2413. Min Act: -0.1700
Data Index: 1675036 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3663. Min Range: -8.3663
Max Act: 8.3663. Min Act: -0.1700
Data Index: 2610794 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3663. Min Range: -8.3663
Max Act: 8.3038. Min Act: -0.1700
Data Index: 712267 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3663. Min Range: -8.3663
Max Act: 8.0538. Min Act: -0.1700
Data Index: 5353455 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3663. Min Range: -8.3663
Max Act: 8.1163. Min Act: -0.1700
Data Index: 409072 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3663. Min Range: -8.3663
Max Act: 8.0225. Min Act: -0.1700
Data Index: 346952 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3663. Min Range: -8.3663
Max Act: 7.9288. Min Act: -0.1700
Data Index: 2610793 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3663. Min Range: -8.3663
Max Act: 7.8663. Min Act: -0.1700
Data Index: 5547839 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3663. Min Range: -8.3663
Max Act: 7.8350. Min Act: -0.1700
Data Index: 712266 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3663. Min Range: -8.3663
Max Act: 7.8663. Min Act: -0.1700
Data Index: 7227922 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3663. Min Range: -8.3663
Max Act: 7.8038. Min Act: -0.1700
Data Index: 371368 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3663. Min Range: -8.3663
Max Act: 7.7413. Min Act: -0.1700
Data Index: 3374549 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3663. Min Range: -8.3663
Max Act: 7.7413. Min Act: -0.1700
Data Index: 7630501 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3663. Min Range: -8.3663
Max Act: 7.7725. Min Act: -0.1700
Data Index: 6878378 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3663. Min Range: -8.3663
Max Act: 7.7413. Min Act: -0.1700
Data Index: 1534445 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3663. Min Range: -8.3663
Max Act: 7.6788. Min Act: -0.1700
Data Index: 4257899 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3663. Min Range: -8.3663
Max Act: 7.6788. Min Act: -0.1700
Data Index: 3164701 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3663. Min Range: -8.3663
Max Act: 7.6475. Min Act: -0.1700
Data Index: 6300938 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #19