Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 74 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.7736. Min Range: -8.7736
Max Act: 8.7736. Min Act: -0.1700
Data Index: 5584869 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7736. Min Range: -8.7736
Max Act: 8.5861. Min Act: -0.1700
Data Index: 3813643 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7736. Min Range: -8.7736
Max Act: 8.2111. Min Act: -0.1700
Data Index: 7067219 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7736. Min Range: -8.7736
Max Act: 8.0236. Min Act: -0.1700
Data Index: 4357069 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7736. Min Range: -8.7736
Max Act: 8.0861. Min Act: -0.1700
Data Index: 6430540 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7736. Min Range: -8.7736
Max Act: 8.0236. Min Act: -0.1700
Data Index: 5314771 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7736. Min Range: -8.7736
Max Act: 8.0236. Min Act: -0.1700
Data Index: 727679 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7736. Min Range: -8.7736
Max Act: 7.9611. Min Act: -0.1700
Data Index: 7325319 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7736. Min Range: -8.7736
Max Act: 7.9611. Min Act: -0.1700
Data Index: 3532455 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7736. Min Range: -8.7736
Max Act: 7.9611. Min Act: -0.1700
Data Index: 2521319 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7736. Min Range: -8.7736
Max Act: 7.9611. Min Act: -0.1700
Data Index: 4809244 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7736. Min Range: -8.7736
Max Act: 7.8986. Min Act: -0.1700
Data Index: 4916284 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7736. Min Range: -8.7736
Max Act: 7.9611. Min Act: -0.1700
Data Index: 489133 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7736. Min Range: -8.7736
Max Act: 7.8986. Min Act: -0.1700
Data Index: 7165214 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7736. Min Range: -8.7736
Max Act: 7.8986. Min Act: -0.1700
Data Index: 5223339 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7736. Min Range: -8.7736
Max Act: 7.8986. Min Act: -0.1700
Data Index: 2328759 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7736. Min Range: -8.7736
Max Act: 7.8986. Min Act: -0.1700
Data Index: 5010967 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7736. Min Range: -8.7736
Max Act: 7.8986. Min Act: -0.1700
Data Index: 404989 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7736. Min Range: -8.7736
Max Act: 7.8986. Min Act: -0.1700
Data Index: 3161908 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7736. Min Range: -8.7736
Max Act: 7.8361. Min Act: -0.1700
Data Index: 2149939 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #19