Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3951 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.1521. Min Range: -11.1521
Max Act: 11.1521. Min Act: -0.1700
Data Index: 4281206 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.1521. Min Range: -11.1521
Max Act: 11.1521. Min Act: -0.1700
Data Index: 6559582 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.1521. Min Range: -11.1521
Max Act: 11.1521. Min Act: -0.1700
Data Index: 5848492 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.1521. Min Range: -11.1521
Max Act: 11.0271. Min Act: -0.1700
Data Index: 7871253 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.1521. Min Range: -11.1521
Max Act: 11.0271. Min Act: -0.1700
Data Index: 4281209 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.1521. Min Range: -11.1521
Max Act: 10.9646. Min Act: -0.1700
Data Index: 368697 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.1521. Min Range: -11.1521
Max Act: 10.9021. Min Act: -0.1700
Data Index: 3813261 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.1521. Min Range: -11.1521
Max Act: 10.9021. Min Act: -0.1700
Data Index: 1036578 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.1521. Min Range: -11.1521
Max Act: 10.7771. Min Act: -0.1700
Data Index: 2905374 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.1521. Min Range: -11.1521
Max Act: 10.7771. Min Act: -0.1700
Data Index: 4801200 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.1521. Min Range: -11.1521
Max Act: 10.7771. Min Act: -0.1700
Data Index: 1247699 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.1521. Min Range: -11.1521
Max Act: 10.7771. Min Act: -0.1700
Data Index: 1036567 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.1521. Min Range: -11.1521
Max Act: 10.7771. Min Act: -0.1700
Data Index: 3343215 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.1521. Min Range: -11.1521
Max Act: 10.7146. Min Act: -0.1700
Data Index: 7127978 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.1521. Min Range: -11.1521
Max Act: 10.6521. Min Act: -0.1700
Data Index: 5344419 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.1521. Min Range: -11.1521
Max Act: 10.7146. Min Act: -0.1700
Data Index: 6127005 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.1521. Min Range: -11.1521
Max Act: 10.7146. Min Act: -0.1700
Data Index: 8815650 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.1521. Min Range: -11.1521
Max Act: 10.7146. Min Act: -0.1700
Data Index: 1316106 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.1521. Min Range: -11.1521
Max Act: 10.6521. Min Act: -0.1700
Data Index: 5848491 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.1521. Min Range: -11.1521
Max Act: 10.6521. Min Act: -0.1700
Data Index: 7041717 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #19