Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 822 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.2410. Min Range: -8.2410
Max Act: 8.2410. Min Act: -0.1700
Data Index: 1682000 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2410. Min Range: -8.2410
Max Act: 8.1160. Min Act: -0.1700
Data Index: 1561612 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2410. Min Range: -8.2410
Max Act: 7.9285. Min Act: -0.1700
Data Index: 3276794 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2410. Min Range: -8.2410
Max Act: 7.8035. Min Act: -0.1700
Data Index: 7025389 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2410. Min Range: -8.2410
Max Act: 7.8035. Min Act: -0.1700
Data Index: 8521571 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2410. Min Range: -8.2410
Max Act: 7.7410. Min Act: -0.1700
Data Index: 2103770 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2410. Min Range: -8.2410
Max Act: 7.6785. Min Act: -0.1700
Data Index: 171568 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2410. Min Range: -8.2410
Max Act: 7.6785. Min Act: -0.1700
Data Index: 3355130 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2410. Min Range: -8.2410
Max Act: 7.6160. Min Act: -0.1700
Data Index: 237168 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2410. Min Range: -8.2410
Max Act: 7.6160. Min Act: -0.1700
Data Index: 5552853 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2410. Min Range: -8.2410
Max Act: 7.6785. Min Act: -0.1700
Data Index: 5377668 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2410. Min Range: -8.2410
Max Act: 7.5535. Min Act: -0.1700
Data Index: 8590568 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2410. Min Range: -8.2410
Max Act: 7.5535. Min Act: -0.1700
Data Index: 7389183 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2410. Min Range: -8.2410
Max Act: 7.5222. Min Act: -0.1700
Data Index: 1279965 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2410. Min Range: -8.2410
Max Act: 7.6160. Min Act: -0.1700
Data Index: 4106375 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2410. Min Range: -8.2410
Max Act: 7.5535. Min Act: -0.1700
Data Index: 171962 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2410. Min Range: -8.2410
Max Act: 7.5222. Min Act: -0.1700
Data Index: 6711736 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2410. Min Range: -8.2410
Max Act: 7.5535. Min Act: -0.1700
Data Index: 4437141 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2410. Min Range: -8.2410
Max Act: 7.4910. Min Act: -0.1700
Data Index: 3276795 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2410. Min Range: -8.2410
Max Act: 7.4910. Min Act: -0.1700
Data Index: 6338795 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #19