Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1633 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.9979. Min Range: -7.9979
Max Act: 7.9979. Min Act: -0.1700
Data Index: 365333 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9979. Min Range: -7.9979
Max Act: 7.9979. Min Act: -0.1700
Data Index: 2315730 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9979. Min Range: -7.9979
Max Act: 7.9666. Min Act: -0.1700
Data Index: 2933911 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9979. Min Range: -7.9979
Max Act: 7.9979. Min Act: -0.1700
Data Index: 2502083 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9979. Min Range: -7.9979
Max Act: 7.8729. Min Act: -0.1700
Data Index: 1352974 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9979. Min Range: -7.9979
Max Act: 7.9354. Min Act: -0.1700
Data Index: 1151830 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9979. Min Range: -7.9979
Max Act: 7.8729. Min Act: -0.1700
Data Index: 5593651 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9979. Min Range: -7.9979
Max Act: 7.7479. Min Act: -0.1700
Data Index: 7322664 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9979. Min Range: -7.9979
Max Act: 7.7166. Min Act: -0.1700
Data Index: 6695720 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9979. Min Range: -7.9979
Max Act: 7.6854. Min Act: -0.1700
Data Index: 177330 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9979. Min Range: -7.9979
Max Act: 7.6854. Min Act: -0.1700
Data Index: 5901081 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9979. Min Range: -7.9979
Max Act: 7.6229. Min Act: -0.1700
Data Index: 2058915 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9979. Min Range: -7.9979
Max Act: 7.6854. Min Act: -0.1700
Data Index: 1691872 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9979. Min Range: -7.9979
Max Act: 7.5916. Min Act: -0.1700
Data Index: 6851553 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9979. Min Range: -7.9979
Max Act: 7.5604. Min Act: -0.1700
Data Index: 7711234 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9979. Min Range: -7.9979
Max Act: 7.5916. Min Act: -0.1700
Data Index: 474552 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9979. Min Range: -7.9979
Max Act: 7.5291. Min Act: -0.1700
Data Index: 457710 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9979. Min Range: -7.9979
Max Act: 7.4666. Min Act: -0.1700
Data Index: 352797 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9979. Min Range: -7.9979
Max Act: 7.4666. Min Act: -0.1700
Data Index: 4083812 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9979. Min Range: -7.9979
Max Act: 7.5291. Min Act: -0.1700
Data Index: 8167490 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #19