Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5036 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9454. Min Range: -6.9454
Max Act: 6.9454. Min Act: -0.1700
Data Index: 4225782 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9454. Min Range: -6.9454
Max Act: 6.7892. Min Act: -0.1700
Data Index: 2062586 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9454. Min Range: -6.9454
Max Act: 6.7267. Min Act: -0.1700
Data Index: 3699774 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9454. Min Range: -6.9454
Max Act: 6.6954. Min Act: -0.1700
Data Index: 5701678 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9454. Min Range: -6.9454
Max Act: 6.6329. Min Act: -0.1700
Data Index: 343264 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9454. Min Range: -6.9454
Max Act: 6.6642. Min Act: -0.1700
Data Index: 8506768 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9454. Min Range: -6.9454
Max Act: 6.6017. Min Act: -0.1700
Data Index: 7790391 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9454. Min Range: -6.9454
Max Act: 6.6017. Min Act: -0.1700
Data Index: 905280 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9454. Min Range: -6.9454
Max Act: 6.6017. Min Act: -0.1700
Data Index: 2871353 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9454. Min Range: -6.9454
Max Act: 6.5704. Min Act: -0.1700
Data Index: 7394516 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9454. Min Range: -6.9454
Max Act: 6.5704. Min Act: -0.1700
Data Index: 5814945 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9454. Min Range: -6.9454
Max Act: 6.5392. Min Act: -0.1700
Data Index: 256883 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9454. Min Range: -6.9454
Max Act: 6.5392. Min Act: -0.1700
Data Index: 6118476 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9454. Min Range: -6.9454
Max Act: 6.5392. Min Act: -0.1700
Data Index: 4939011 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9454. Min Range: -6.9454
Max Act: 6.5079. Min Act: -0.1700
Data Index: 7259218 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9454. Min Range: -6.9454
Max Act: 6.5079. Min Act: -0.1700
Data Index: 673473 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9454. Min Range: -6.9454
Max Act: 6.4767. Min Act: -0.1700
Data Index: 7817484 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9454. Min Range: -6.9454
Max Act: 6.4767. Min Act: -0.1700
Data Index: 2228361 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9454. Min Range: -6.9454
Max Act: 6.4767. Min Act: -0.1700
Data Index: 6568173 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9454. Min Range: -6.9454
Max Act: 6.4767. Min Act: -0.1700
Data Index: 4271692 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #19