Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4075 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.0685. Min Range: -3.0685
Max Act: 3.0685. Min Act: -0.1700
Data Index: 2395318 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0685. Min Range: -3.0685
Max Act: 3.0053. Min Act: -0.1700
Data Index: 4970941 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0685. Min Range: -3.0685
Max Act: 3.0053. Min Act: -0.1700
Data Index: 3700996 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0685. Min Range: -3.0685
Max Act: 3.0053. Min Act: -0.1700
Data Index: 7415004 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0685. Min Range: -3.0685
Max Act: 2.9421. Min Act: -0.1700
Data Index: 694745 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0685. Min Range: -3.0685
Max Act: 2.9579. Min Act: -0.1700
Data Index: 6501362 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0685. Min Range: -3.0685
Max Act: 2.9579. Min Act: -0.1700
Data Index: 872247 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0685. Min Range: -3.0685
Max Act: 2.9579. Min Act: -0.1700
Data Index: 593410 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0685. Min Range: -3.0685
Max Act: 2.9579. Min Act: -0.1700
Data Index: 4225729 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0685. Min Range: -3.0685
Max Act: 2.9421. Min Act: -0.1700
Data Index: 2856275 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0685. Min Range: -3.0685
Max Act: 2.9421. Min Act: -0.1700
Data Index: 2005946 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0685. Min Range: -3.0685
Max Act: 2.9262. Min Act: -0.1700
Data Index: 5997692 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0685. Min Range: -3.0685
Max Act: 2.9421. Min Act: -0.1700
Data Index: 7106469 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0685. Min Range: -3.0685
Max Act: 2.9104. Min Act: -0.1700
Data Index: 8395600 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0685. Min Range: -3.0685
Max Act: 2.9262. Min Act: -0.1700
Data Index: 3990808 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0685. Min Range: -3.0685
Max Act: 2.8945. Min Act: -0.1700
Data Index: 6339650 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0685. Min Range: -3.0685
Max Act: 2.8945. Min Act: -0.1700
Data Index: 8531777 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0685. Min Range: -3.0685
Max Act: 2.8787. Min Act: -0.1700
Data Index: 8182784 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0685. Min Range: -3.0685
Max Act: 2.8628. Min Act: -0.1700
Data Index: 3613808 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0685. Min Range: -3.0685
Max Act: 2.8945. Min Act: -0.1700
Data Index: 675859 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #19