Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 746 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.9291. Min Range: -5.9291
Max Act: 5.9291. Min Act: -0.1700
Data Index: 5187685 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9291. Min Range: -5.9291
Max Act: 5.8354. Min Act: -0.1700
Data Index: 908303 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9291. Min Range: -5.9291
Max Act: 5.8041. Min Act: -0.1700
Data Index: 8731862 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9291. Min Range: -5.9291
Max Act: 5.7104. Min Act: -0.1700
Data Index: 7421901 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9291. Min Range: -5.9291
Max Act: 5.6166. Min Act: -0.1700
Data Index: 8639037 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9291. Min Range: -5.9291
Max Act: 5.6479. Min Act: -0.1700
Data Index: 3618317 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9291. Min Range: -5.9291
Max Act: 5.5854. Min Act: -0.1700
Data Index: 5861263 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9291. Min Range: -5.9291
Max Act: 5.5854. Min Act: -0.1700
Data Index: 5049103 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9291. Min Range: -5.9291
Max Act: 5.4916. Min Act: -0.1700
Data Index: 3789928 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9291. Min Range: -5.9291
Max Act: 5.4916. Min Act: -0.1700
Data Index: 3789931 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9291. Min Range: -5.9291
Max Act: 5.4291. Min Act: -0.1700
Data Index: 1751656 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9291. Min Range: -5.9291
Max Act: 5.3979. Min Act: -0.1700
Data Index: 4333910 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9291. Min Range: -5.9291
Max Act: 5.3979. Min Act: -0.1700
Data Index: 8267781 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9291. Min Range: -5.9291
Max Act: 5.3666. Min Act: -0.1700
Data Index: 3206208 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9291. Min Range: -5.9291
Max Act: 5.3666. Min Act: -0.1700
Data Index: 758409 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9291. Min Range: -5.9291
Max Act: 5.3354. Min Act: -0.1700
Data Index: 2019106 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9291. Min Range: -5.9291
Max Act: 5.3666. Min Act: -0.1700
Data Index: 3801419 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9291. Min Range: -5.9291
Max Act: 5.3354. Min Act: -0.1700
Data Index: 5038890 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9291. Min Range: -5.9291
Max Act: 5.2729. Min Act: -0.1700
Data Index: 646112 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9291. Min Range: -5.9291
Max Act: 5.2729. Min Act: -0.1700
Data Index: 3659393 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #19