Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1793 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.7674. Min Range: -4.7674
Max Act: 4.7674. Min Act: -0.1700
Data Index: 2991267 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7674. Min Range: -4.7674
Max Act: 4.6112. Min Act: -0.1700
Data Index: 3382872 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7674. Min Range: -4.7674
Max Act: 4.5799. Min Act: -0.1700
Data Index: 8465755 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7674. Min Range: -4.7674
Max Act: 4.5174. Min Act: -0.1700
Data Index: 8707720 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7674. Min Range: -4.7674
Max Act: 4.5799. Min Act: -0.1700
Data Index: 4078505 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7674. Min Range: -4.7674
Max Act: 4.5487. Min Act: -0.1700
Data Index: 574155 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7674. Min Range: -4.7674
Max Act: 4.4862. Min Act: -0.1700
Data Index: 6078164 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7674. Min Range: -4.7674
Max Act: 4.5174. Min Act: -0.1700
Data Index: 5542567 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7674. Min Range: -4.7674
Max Act: 4.5174. Min Act: -0.1700
Data Index: 6464357 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7674. Min Range: -4.7674
Max Act: 4.4862. Min Act: -0.1700
Data Index: 8353698 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7674. Min Range: -4.7674
Max Act: 4.4862. Min Act: -0.1700
Data Index: 3668956 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7674. Min Range: -4.7674
Max Act: 4.4237. Min Act: -0.1700
Data Index: 2991264 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7674. Min Range: -4.7674
Max Act: 4.4237. Min Act: -0.1700
Data Index: 653348 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7674. Min Range: -4.7674
Max Act: 4.4237. Min Act: -0.1700
Data Index: 8202687 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7674. Min Range: -4.7674
Max Act: 4.3924. Min Act: -0.1700
Data Index: 7034518 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7674. Min Range: -4.7674
Max Act: 4.3924. Min Act: -0.1700
Data Index: 7495168 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7674. Min Range: -4.7674
Max Act: 4.3924. Min Act: -0.1700
Data Index: 3146121 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7674. Min Range: -4.7674
Max Act: 4.3924. Min Act: -0.1700
Data Index: 4722647 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7674. Min Range: -4.7674
Max Act: 4.4237. Min Act: -0.1700
Data Index: 653358 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7674. Min Range: -4.7674
Max Act: 4.3612. Min Act: -0.1700
Data Index: 5663443 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #19