Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 545 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4983. Min Range: -7.4983
Max Act: 7.4983. Min Act: -0.1700
Data Index: 7843185 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4983. Min Range: -7.4983
Max Act: 7.2795. Min Act: -0.1700
Data Index: 5392696 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4983. Min Range: -7.4983
Max Act: 7.2170. Min Act: -0.1700
Data Index: 5392697 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4983. Min Range: -7.4983
Max Act: 7.1545. Min Act: -0.1700
Data Index: 2687416 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4983. Min Range: -7.4983
Max Act: 7.0920. Min Act: -0.1700
Data Index: 4795186 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4983. Min Range: -7.4983
Max Act: 7.0920. Min Act: -0.1700
Data Index: 8779139 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4983. Min Range: -7.4983
Max Act: 6.9983. Min Act: -0.1700
Data Index: 7336921 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4983. Min Range: -7.4983
Max Act: 6.9983. Min Act: -0.1700
Data Index: 7501714 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4983. Min Range: -7.4983
Max Act: 6.9670. Min Act: -0.1700
Data Index: 4774930 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4983. Min Range: -7.4983
Max Act: 6.8733. Min Act: -0.1700
Data Index: 8617728 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4983. Min Range: -7.4983
Max Act: 6.8420. Min Act: -0.1700
Data Index: 2813426 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4983. Min Range: -7.4983
Max Act: 6.8733. Min Act: -0.1700
Data Index: 210864 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4983. Min Range: -7.4983
Max Act: 6.8733. Min Act: -0.1700
Data Index: 8122969 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4983. Min Range: -7.4983
Max Act: 6.8420. Min Act: -0.1700
Data Index: 5188269 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4983. Min Range: -7.4983
Max Act: 6.8420. Min Act: -0.1700
Data Index: 1792118 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4983. Min Range: -7.4983
Max Act: 6.7795. Min Act: -0.1700
Data Index: 8384051 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4983. Min Range: -7.4983
Max Act: 6.7795. Min Act: -0.1700
Data Index: 1219799 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4983. Min Range: -7.4983
Max Act: 6.7483. Min Act: -0.1700
Data Index: 7008492 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4983. Min Range: -7.4983
Max Act: 6.7483. Min Act: -0.1700
Data Index: 3891255 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4983. Min Range: -7.4983
Max Act: 6.7483. Min Act: -0.1700
Data Index: 1056075 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #19