Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2273 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4883. Min Range: -8.4883
Max Act: 8.4883. Min Act: -0.1700
Data Index: 3074890 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4883. Min Range: -8.4883
Max Act: 8.2383. Min Act: -0.1700
Data Index: 6108783 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4883. Min Range: -8.4883
Max Act: 8.2070. Min Act: -0.1700
Data Index: 4273729 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4883. Min Range: -8.4883
Max Act: 8.1133. Min Act: -0.1698
Data Index: 4973335 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4883. Min Range: -8.4883
Max Act: 8.0195. Min Act: -0.1700
Data Index: 6556084 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4883. Min Range: -8.4883
Max Act: 8.0195. Min Act: -0.1700
Data Index: 4985321 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4883. Min Range: -8.4883
Max Act: 7.9883. Min Act: -0.1700
Data Index: 3831714 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4883. Min Range: -8.4883
Max Act: 7.9570. Min Act: -0.1700
Data Index: 2938449 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4883. Min Range: -8.4883
Max Act: 7.9883. Min Act: -0.1700
Data Index: 4056043 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4883. Min Range: -8.4883
Max Act: 7.8633. Min Act: -0.1700
Data Index: 7934639 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4883. Min Range: -8.4883
Max Act: 7.8320. Min Act: -0.1700
Data Index: 741948 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4883. Min Range: -8.4883
Max Act: 7.8320. Min Act: -0.1700
Data Index: 3935061 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4883. Min Range: -8.4883
Max Act: 7.8320. Min Act: -0.1700
Data Index: 1538417 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4883. Min Range: -8.4883
Max Act: 7.8008. Min Act: -0.1700
Data Index: 3879547 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4883. Min Range: -8.4883
Max Act: 7.7383. Min Act: -0.1700
Data Index: 3128232 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4883. Min Range: -8.4883
Max Act: 7.7695. Min Act: -0.1700
Data Index: 806897 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4883. Min Range: -8.4883
Max Act: 7.8008. Min Act: -0.1700
Data Index: 758658 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4883. Min Range: -8.4883
Max Act: 7.7383. Min Act: -0.1700
Data Index: 2456932 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4883. Min Range: -8.4883
Max Act: 7.7695. Min Act: -0.1700
Data Index: 6288410 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4883. Min Range: -8.4883
Max Act: 7.7695. Min Act: -0.1700
Data Index: 6388120 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #19