Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1769 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.5703. Min Range: -10.5703
Max Act: 10.5703. Min Act: -0.1700
Data Index: 2842083 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.5703. Min Range: -10.5703
Max Act: 10.3828. Min Act: -0.1700
Data Index: 558425 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.5703. Min Range: -10.5703
Max Act: 10.3203. Min Act: -0.1700
Data Index: 6755677 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.5703. Min Range: -10.5703
Max Act: 10.3203. Min Act: -0.1700
Data Index: 7170243 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.5703. Min Range: -10.5703
Max Act: 10.2578. Min Act: -0.1700
Data Index: 3269325 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.5703. Min Range: -10.5703
Max Act: 10.0703. Min Act: -0.1700
Data Index: 4945988 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.5703. Min Range: -10.5703
Max Act: 10.1328. Min Act: -0.1700
Data Index: 6624250 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.5703. Min Range: -10.5703
Max Act: 10.1328. Min Act: -0.1700
Data Index: 7038589 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.5703. Min Range: -10.5703
Max Act: 10.0703. Min Act: -0.1700
Data Index: 5144298 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.5703. Min Range: -10.5703
Max Act: 10.0703. Min Act: -0.1700
Data Index: 1141874 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.5703. Min Range: -10.5703
Max Act: 10.0703. Min Act: -0.1700
Data Index: 8488593 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.5703. Min Range: -10.5703
Max Act: 10.0078. Min Act: -0.1700
Data Index: 352589 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.5703. Min Range: -10.5703
Max Act: 10.0078. Min Act: -0.1700
Data Index: 3941923 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.5703. Min Range: -10.5703
Max Act: 10.0703. Min Act: -0.1700
Data Index: 7897039 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.5703. Min Range: -10.5703
Max Act: 9.9453. Min Act: -0.1700
Data Index: 8471430 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.5703. Min Range: -10.5703
Max Act: 9.9453. Min Act: -0.1700
Data Index: 4881768 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.5703. Min Range: -10.5703
Max Act: 10.0078. Min Act: -0.1700
Data Index: 6755665 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.5703. Min Range: -10.5703
Max Act: 10.0078. Min Act: -0.1700
Data Index: 3369584 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.5703. Min Range: -10.5703
Max Act: 10.0078. Min Act: -0.1700
Data Index: 1237391 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.5703. Min Range: -10.5703
Max Act: 10.0078. Min Act: -0.1700
Data Index: 3557020 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #19