Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1085 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2038. Min Range: -6.2038
Max Act: 6.2038. Min Act: -0.1700
Data Index: 4195400 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2038. Min Range: -6.2038
Max Act: 6.1101. Min Act: -0.1700
Data Index: 6501587 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2038. Min Range: -6.2038
Max Act: 6.0476. Min Act: -0.1700
Data Index: 3583603 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2038. Min Range: -6.2038
Max Act: 5.9851. Min Act: -0.1700
Data Index: 8014502 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2038. Min Range: -6.2038
Max Act: 5.8913. Min Act: -0.1700
Data Index: 3583602 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2038. Min Range: -6.2038
Max Act: 5.7351. Min Act: -0.1700
Data Index: 149467 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2038. Min Range: -6.2038
Max Act: 5.7351. Min Act: -0.1700
Data Index: 5304999 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2038. Min Range: -6.2038
Max Act: 5.7038. Min Act: -0.1700
Data Index: 5794793 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2038. Min Range: -6.2038
Max Act: 5.6413. Min Act: -0.1700
Data Index: 1535789 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2038. Min Range: -6.2038
Max Act: 5.6726. Min Act: -0.1700
Data Index: 892865 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2038. Min Range: -6.2038
Max Act: 5.6101. Min Act: -0.1700
Data Index: 1811194 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2038. Min Range: -6.2038
Max Act: 5.6101. Min Act: -0.1700
Data Index: 4491753 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2038. Min Range: -6.2038
Max Act: 5.6101. Min Act: -0.1700
Data Index: 7940872 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2038. Min Range: -6.2038
Max Act: 5.5788. Min Act: -0.1700
Data Index: 2379067 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2038. Min Range: -6.2038
Max Act: 5.5476. Min Act: -0.1700
Data Index: 2222741 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2038. Min Range: -6.2038
Max Act: 5.5476. Min Act: -0.1700
Data Index: 1441137 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2038. Min Range: -6.2038
Max Act: 5.5163. Min Act: -0.1700
Data Index: 732352 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2038. Min Range: -6.2038
Max Act: 5.4851. Min Act: -0.1700
Data Index: 969647 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2038. Min Range: -6.2038
Max Act: 5.4851. Min Act: -0.1700
Data Index: 1244330 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2038. Min Range: -6.2038
Max Act: 5.4851. Min Act: -0.1700
Data Index: 248322 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #19