Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3652 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4145. Min Range: -4.4145
Max Act: 4.4145. Min Act: -0.1700
Data Index: 3457801 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4145. Min Range: -4.4145
Max Act: 4.4145. Min Act: -0.1700
Data Index: 3457799 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4145. Min Range: -4.4145
Max Act: 4.3520. Min Act: -0.1700
Data Index: 61826 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4145. Min Range: -4.4145
Max Act: 4.2582. Min Act: -0.1700
Data Index: 5962183 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4145. Min Range: -4.4145
Max Act: 4.2582. Min Act: -0.1700
Data Index: 640121 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4145. Min Range: -4.4145
Max Act: 4.2270. Min Act: -0.1700
Data Index: 3363304 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4145. Min Range: -4.4145
Max Act: 4.1645. Min Act: -0.1700
Data Index: 6684504 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4145. Min Range: -4.4145
Max Act: 4.1645. Min Act: -0.1700
Data Index: 5021800 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4145. Min Range: -4.4145
Max Act: 4.1332. Min Act: -0.1700
Data Index: 1341828 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4145. Min Range: -4.4145
Max Act: 4.1020. Min Act: -0.1700
Data Index: 5642653 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4145. Min Range: -4.4145
Max Act: 4.1020. Min Act: -0.1700
Data Index: 5548893 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4145. Min Range: -4.4145
Max Act: 4.1020. Min Act: -0.1700
Data Index: 3436689 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4145. Min Range: -4.4145
Max Act: 4.1020. Min Act: -0.1700
Data Index: 4514366 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4145. Min Range: -4.4145
Max Act: 4.1020. Min Act: -0.1700
Data Index: 2275047 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4145. Min Range: -4.4145
Max Act: 4.1020. Min Act: -0.1700
Data Index: 7668391 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4145. Min Range: -4.4145
Max Act: 4.0707. Min Act: -0.1700
Data Index: 8037709 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4145. Min Range: -4.4145
Max Act: 4.0707. Min Act: -0.1700
Data Index: 5671403 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4145. Min Range: -4.4145
Max Act: 4.0707. Min Act: -0.1700
Data Index: 7686485 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4145. Min Range: -4.4145
Max Act: 4.0707. Min Act: -0.1700
Data Index: 5963895 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4145. Min Range: -4.4145
Max Act: 4.0707. Min Act: -0.1700
Data Index: 6684511 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #19