Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 474 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9051. Min Range: -6.9051
Max Act: 6.8426. Min Act: -0.1700
Data Index: 2451726 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9051. Min Range: -6.9051
Max Act: 6.8738. Min Act: -0.1700
Data Index: 7504328 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9051. Min Range: -6.9051
Max Act: 6.9051. Min Act: -0.1700
Data Index: 6695553 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9051. Min Range: -6.9051
Max Act: 6.8113. Min Act: -0.1700
Data Index: 2015920 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9051. Min Range: -6.9051
Max Act: 6.8113. Min Act: -0.1700
Data Index: 2217605 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9051. Min Range: -6.9051
Max Act: 6.7176. Min Act: -0.1700
Data Index: 1330944 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9051. Min Range: -6.9051
Max Act: 6.7176. Min Act: -0.1699
Data Index: 7935446 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9051. Min Range: -6.9051
Max Act: 6.6863. Min Act: -0.1700
Data Index: 7935444 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9051. Min Range: -6.9051
Max Act: 6.6551. Min Act: -0.1700
Data Index: 7883587 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9051. Min Range: -6.9051
Max Act: 6.6551. Min Act: -0.1700
Data Index: 4043348 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9051. Min Range: -6.9051
Max Act: 6.6863. Min Act: -0.1700
Data Index: 6704470 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9051. Min Range: -6.9051
Max Act: 6.6238. Min Act: -0.1700
Data Index: 5789581 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9051. Min Range: -6.9051
Max Act: 6.6238. Min Act: -0.1700
Data Index: 6400968 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9051. Min Range: -6.9051
Max Act: 6.5926. Min Act: -0.1700
Data Index: 6744183 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9051. Min Range: -6.9051
Max Act: 6.5613. Min Act: -0.1700
Data Index: 7730455 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9051. Min Range: -6.9051
Max Act: 6.5613. Min Act: -0.1700
Data Index: 2996919 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9051. Min Range: -6.9051
Max Act: 6.5613. Min Act: -0.1700
Data Index: 7034100 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9051. Min Range: -6.9051
Max Act: 6.5613. Min Act: -0.1700
Data Index: 3293509 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9051. Min Range: -6.9051
Max Act: 6.5613. Min Act: -0.1700
Data Index: 5603877 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9051. Min Range: -6.9051
Max Act: 6.5613. Min Act: -0.1700
Data Index: 4998026 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #19