Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5462 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6511. Min Range: -7.6511
Max Act: 7.6511. Min Act: -0.1700
Data Index: 3095138 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6511. Min Range: -7.6511
Max Act: 7.2761. Min Act: -0.1700
Data Index: 705796 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6511. Min Range: -7.6511
Max Act: 7.1198. Min Act: -0.1700
Data Index: 1366369 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6511. Min Range: -7.6511
Max Act: 7.1198. Min Act: -0.1700
Data Index: 7429696 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6511. Min Range: -7.6511
Max Act: 7.0573. Min Act: -0.1700
Data Index: 7261828 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6511. Min Range: -7.6511
Max Act: 6.9948. Min Act: -0.1700
Data Index: 5527153 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6511. Min Range: -7.6511
Max Act: 6.9948. Min Act: -0.1700
Data Index: 3894575 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6511. Min Range: -7.6511
Max Act: 6.9948. Min Act: -0.1700
Data Index: 8016335 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6511. Min Range: -7.6511
Max Act: 6.9636. Min Act: -0.1700
Data Index: 8674200 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6511. Min Range: -7.6511
Max Act: 6.9948. Min Act: -0.1700
Data Index: 4901184 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6511. Min Range: -7.6511
Max Act: 6.9636. Min Act: -0.1700
Data Index: 4827854 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6511. Min Range: -7.6511
Max Act: 6.9323. Min Act: -0.1700
Data Index: 2523888 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6511. Min Range: -7.6511
Max Act: 6.9323. Min Act: -0.1700
Data Index: 4544301 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6511. Min Range: -7.6511
Max Act: 6.9323. Min Act: -0.1700
Data Index: 2095205 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6511. Min Range: -7.6511
Max Act: 6.9011. Min Act: -0.1700
Data Index: 6544989 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6511. Min Range: -7.6511
Max Act: 6.9011. Min Act: -0.1700
Data Index: 7923569 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6511. Min Range: -7.6511
Max Act: 6.8386. Min Act: -0.1700
Data Index: 255548 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6511. Min Range: -7.6511
Max Act: 6.8386. Min Act: -0.1700
Data Index: 3972196 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6511. Min Range: -7.6511
Max Act: 6.8698. Min Act: -0.1700
Data Index: 1909687 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6511. Min Range: -7.6511
Max Act: 6.8698. Min Act: -0.1700
Data Index: 1128584 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #19