Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1947 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1674. Min Range: -7.1674
Max Act: 7.1674. Min Act: -0.1700
Data Index: 5314496 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1674. Min Range: -7.1674
Max Act: 6.9799. Min Act: -0.1700
Data Index: 3571660 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1674. Min Range: -7.1674
Max Act: 7.0112. Min Act: -0.1700
Data Index: 650750 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1674. Min Range: -7.1674
Max Act: 6.9487. Min Act: -0.1700
Data Index: 29762 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1674. Min Range: -7.1674
Max Act: 6.9487. Min Act: -0.1700
Data Index: 3708543 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1674. Min Range: -7.1674
Max Act: 6.8862. Min Act: -0.1700
Data Index: 8669608 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1674. Min Range: -7.1674
Max Act: 6.8549. Min Act: -0.1700
Data Index: 3936840 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1674. Min Range: -7.1674
Max Act: 6.8549. Min Act: -0.1700
Data Index: 7919702 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1674. Min Range: -7.1674
Max Act: 6.7924. Min Act: -0.1700
Data Index: 1212252 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1674. Min Range: -7.1674
Max Act: 6.7924. Min Act: -0.1700
Data Index: 7315474 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1674. Min Range: -7.1674
Max Act: 6.7924. Min Act: -0.1700
Data Index: 3999534 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1674. Min Range: -7.1674
Max Act: 6.7612. Min Act: -0.1700
Data Index: 5865663 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1674. Min Range: -7.1674
Max Act: 6.7299. Min Act: -0.1700
Data Index: 7355783 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1674. Min Range: -7.1674
Max Act: 6.7612. Min Act: -0.1700
Data Index: 5045325 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1674. Min Range: -7.1674
Max Act: 6.7612. Min Act: -0.1700
Data Index: 7322831 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1674. Min Range: -7.1674
Max Act: 6.7299. Min Act: -0.1700
Data Index: 1729535 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1674. Min Range: -7.1674
Max Act: 6.7299. Min Act: -0.1700
Data Index: 4395450 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1674. Min Range: -7.1674
Max Act: 6.7299. Min Act: -0.1700
Data Index: 7790014 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1674. Min Range: -7.1674
Max Act: 6.7299. Min Act: -0.1700
Data Index: 2111297 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1674. Min Range: -7.1674
Max Act: 6.7299. Min Act: -0.1700
Data Index: 841484 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #19