Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5808 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.0868. Min Range: -9.0868
Max Act: 9.0868. Min Act: -0.1700
Data Index: 258069 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0868. Min Range: -9.0868
Max Act: 9.0868. Min Act: -0.1700
Data Index: 792025 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0868. Min Range: -9.0868
Max Act: 8.8993. Min Act: -0.1700
Data Index: 3022204 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0868. Min Range: -9.0868
Max Act: 8.8368. Min Act: -0.1700
Data Index: 2658981 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0868. Min Range: -9.0868
Max Act: 8.7743. Min Act: -0.1700
Data Index: 4208451 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0868. Min Range: -9.0868
Max Act: 8.7743. Min Act: -0.1700
Data Index: 4513347 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0868. Min Range: -9.0868
Max Act: 8.7118. Min Act: -0.1700
Data Index: 959199 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0868. Min Range: -9.0868
Max Act: 8.6493. Min Act: -0.1700
Data Index: 186217 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0868. Min Range: -9.0868
Max Act: 8.6493. Min Act: -0.1700
Data Index: 7665124 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0868. Min Range: -9.0868
Max Act: 8.6493. Min Act: -0.1700
Data Index: 6033954 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0868. Min Range: -9.0868
Max Act: 8.5868. Min Act: -0.1700
Data Index: 8093634 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0868. Min Range: -9.0868
Max Act: 8.5868. Min Act: -0.1700
Data Index: 7399451 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0868. Min Range: -9.0868
Max Act: 8.5243. Min Act: -0.1700
Data Index: 2645663 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0868. Min Range: -9.0868
Max Act: 8.4618. Min Act: -0.1700
Data Index: 7833292 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0868. Min Range: -9.0868
Max Act: 8.4618. Min Act: -0.1700
Data Index: 6543431 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0868. Min Range: -9.0868
Max Act: 8.4618. Min Act: -0.1700
Data Index: 984945 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0868. Min Range: -9.0868
Max Act: 8.4618. Min Act: -0.1700
Data Index: 902616 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0868. Min Range: -9.0868
Max Act: 8.4618. Min Act: -0.1700
Data Index: 422425 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0868. Min Range: -9.0868
Max Act: 8.4618. Min Act: -0.1700
Data Index: 5612351 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0868. Min Range: -9.0868
Max Act: 8.4618. Min Act: -0.1700
Data Index: 2918552 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #19