Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3952 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.4154. Min Range: -9.4154
Max Act: 9.4154. Min Act: -0.1700
Data Index: 6650621 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.4154. Min Range: -9.4154
Max Act: 9.3529. Min Act: -0.1700
Data Index: 344612 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.4154. Min Range: -9.4154
Max Act: 9.1654. Min Act: -0.1700
Data Index: 5713746 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.4154. Min Range: -9.4154
Max Act: 9.1654. Min Act: -0.1700
Data Index: 6566418 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.4154. Min Range: -9.4154
Max Act: 9.1029. Min Act: -0.1700
Data Index: 4572579 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.4154. Min Range: -9.4154
Max Act: 9.1029. Min Act: -0.1700
Data Index: 2000730 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.4154. Min Range: -9.4154
Max Act: 9.0404. Min Act: -0.1700
Data Index: 5887156 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.4154. Min Range: -9.4154
Max Act: 8.8529. Min Act: -0.1700
Data Index: 5453465 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.4154. Min Range: -9.4154
Max Act: 8.7904. Min Act: -0.1700
Data Index: 3508229 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.4154. Min Range: -9.4154
Max Act: 8.7279. Min Act: -0.1700
Data Index: 8325656 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.4154. Min Range: -9.4154
Max Act: 8.7279. Min Act: -0.1700
Data Index: 1361901 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.4154. Min Range: -9.4154
Max Act: 8.6654. Min Act: -0.1700
Data Index: 8399828 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.4154. Min Range: -9.4154
Max Act: 8.6654. Min Act: -0.1700
Data Index: 5052758 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.4154. Min Range: -9.4154
Max Act: 8.6029. Min Act: -0.1700
Data Index: 335873 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.4154. Min Range: -9.4154
Max Act: 8.6029. Min Act: -0.1700
Data Index: 7460225 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.4154. Min Range: -9.4154
Max Act: 8.6654. Min Act: -0.1700
Data Index: 192907 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.4154. Min Range: -9.4154
Max Act: 8.5404. Min Act: -0.1700
Data Index: 5468812 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.4154. Min Range: -9.4154
Max Act: 8.6029. Min Act: -0.1700
Data Index: 6700744 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.4154. Min Range: -9.4154
Max Act: 8.5404. Min Act: -0.1700
Data Index: 6788181 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.4154. Min Range: -9.4154
Max Act: 8.5404. Min Act: -0.1700
Data Index: 7705481 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #19