Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1306 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6279. Min Range: -5.6279
Max Act: 5.6279. Min Act: -0.1700
Data Index: 8068820 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6279. Min Range: -5.6279
Max Act: 5.2842. Min Act: -0.1700
Data Index: 6923014 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6279. Min Range: -5.6279
Max Act: 5.2217. Min Act: -0.1700
Data Index: 4679801 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6279. Min Range: -5.6279
Max Act: 5.0967. Min Act: -0.1700
Data Index: 1650623 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6279. Min Range: -5.6279
Max Act: 5.0654. Min Act: -0.1700
Data Index: 4340336 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6279. Min Range: -5.6279
Max Act: 5.0342. Min Act: -0.1700
Data Index: 8503235 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6279. Min Range: -5.6279
Max Act: 5.0029. Min Act: -0.1700
Data Index: 3579432 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6279. Min Range: -5.6279
Max Act: 4.9717. Min Act: -0.1700
Data Index: 7058276 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6279. Min Range: -5.6279
Max Act: 4.9404. Min Act: -0.1700
Data Index: 3832172 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6279. Min Range: -5.6279
Max Act: 4.9404. Min Act: -0.1700
Data Index: 1144748 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6279. Min Range: -5.6279
Max Act: 4.9092. Min Act: -0.1700
Data Index: 4696203 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6279. Min Range: -5.6279
Max Act: 4.8779. Min Act: -0.1700
Data Index: 5603067 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6279. Min Range: -5.6279
Max Act: 4.9092. Min Act: -0.1700
Data Index: 6287441 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6279. Min Range: -5.6279
Max Act: 4.9092. Min Act: -0.1700
Data Index: 7805773 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6279. Min Range: -5.6279
Max Act: 4.8779. Min Act: -0.1700
Data Index: 3049140 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6279. Min Range: -5.6279
Max Act: 4.8779. Min Act: -0.1700
Data Index: 4102386 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6279. Min Range: -5.6279
Max Act: 4.9092. Min Act: -0.1700
Data Index: 6389360 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6279. Min Range: -5.6279
Max Act: 4.8779. Min Act: -0.1700
Data Index: 2847908 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6279. Min Range: -5.6279
Max Act: 4.8779. Min Act: -0.1700
Data Index: 6505422 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6279. Min Range: -5.6279
Max Act: 4.8779. Min Act: -0.1700
Data Index: 5472115 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #19