Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 276 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8681. Min Range: -6.8681
Max Act: 6.8681. Min Act: -0.1700
Data Index: 1164844 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8681. Min Range: -6.8681
Max Act: 6.4931. Min Act: -0.1700
Data Index: 7339973 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8681. Min Range: -6.8681
Max Act: 6.4619. Min Act: -0.1700
Data Index: 4642761 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8681. Min Range: -6.8681
Max Act: 6.4619. Min Act: -0.1700
Data Index: 1373052 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8681. Min Range: -6.8681
Max Act: 6.4306. Min Act: -0.1700
Data Index: 1962135 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8681. Min Range: -6.8681
Max Act: 6.3994. Min Act: -0.1700
Data Index: 6703893 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8681. Min Range: -6.8681
Max Act: 6.4306. Min Act: -0.1700
Data Index: 5289863 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8681. Min Range: -6.8681
Max Act: 6.3681. Min Act: -0.1700
Data Index: 5589010 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8681. Min Range: -6.8681
Max Act: 6.2744. Min Act: -0.1700
Data Index: 744026 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8681. Min Range: -6.8681
Max Act: 6.2119. Min Act: -0.1700
Data Index: 1950850 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8681. Min Range: -6.8681
Max Act: 6.1806. Min Act: -0.1700
Data Index: 3679867 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8681. Min Range: -6.8681
Max Act: 6.1494. Min Act: -0.1700
Data Index: 345291 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8681. Min Range: -6.8681
Max Act: 6.1494. Min Act: -0.1700
Data Index: 7730325 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8681. Min Range: -6.8681
Max Act: 6.1181. Min Act: -0.1700
Data Index: 2809674 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8681. Min Range: -6.8681
Max Act: 6.1806. Min Act: -0.1700
Data Index: 1148559 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8681. Min Range: -6.8681
Max Act: 6.1494. Min Act: -0.1700
Data Index: 32189 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8681. Min Range: -6.8681
Max Act: 6.1494. Min Act: -0.1700
Data Index: 337479 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8681. Min Range: -6.8681
Max Act: 6.1181. Min Act: -0.1700
Data Index: 1834966 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8681. Min Range: -6.8681
Max Act: 6.1181. Min Act: -0.1700
Data Index: 2809686 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8681. Min Range: -6.8681
Max Act: 6.1181. Min Act: -0.1700
Data Index: 6003056 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #19