Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4697 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9005. Min Range: -6.9005
Max Act: 6.9005. Min Act: -0.1700
Data Index: 5582007 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9005. Min Range: -6.9005
Max Act: 6.8068. Min Act: -0.1700
Data Index: 3581306 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9005. Min Range: -6.9005
Max Act: 6.7443. Min Act: -0.1700
Data Index: 4732580 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9005. Min Range: -6.9005
Max Act: 6.6818. Min Act: -0.1700
Data Index: 1621413 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9005. Min Range: -6.9005
Max Act: 6.6505. Min Act: -0.1700
Data Index: 2798393 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9005. Min Range: -6.9005
Max Act: 6.5880. Min Act: -0.1700
Data Index: 8476832 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9005. Min Range: -6.9005
Max Act: 6.5568. Min Act: -0.1700
Data Index: 7077952 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9005. Min Range: -6.9005
Max Act: 6.5255. Min Act: -0.1700
Data Index: 5622506 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9005. Min Range: -6.9005
Max Act: 6.4943. Min Act: -0.1700
Data Index: 453817 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9005. Min Range: -6.9005
Max Act: 6.4630. Min Act: -0.1700
Data Index: 6692183 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9005. Min Range: -6.9005
Max Act: 6.4318. Min Act: -0.1700
Data Index: 3619298 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9005. Min Range: -6.9005
Max Act: 6.4005. Min Act: -0.1700
Data Index: 8107266 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9005. Min Range: -6.9005
Max Act: 6.4005. Min Act: -0.1700
Data Index: 5775004 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9005. Min Range: -6.9005
Max Act: 6.3693. Min Act: -0.1700
Data Index: 7841517 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9005. Min Range: -6.9005
Max Act: 6.3693. Min Act: -0.1700
Data Index: 2875849 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9005. Min Range: -6.9005
Max Act: 6.3693. Min Act: -0.1700
Data Index: 5654313 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9005. Min Range: -6.9005
Max Act: 6.3380. Min Act: -0.1700
Data Index: 6731207 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9005. Min Range: -6.9005
Max Act: 6.3068. Min Act: -0.1700
Data Index: 5775001 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9005. Min Range: -6.9005
Max Act: 6.2755. Min Act: -0.1700
Data Index: 585373 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9005. Min Range: -6.9005
Max Act: 6.2755. Min Act: -0.1700
Data Index: 6465351 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #19