Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1970 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.0786. Min Range: -3.0786
Max Act: 3.0786. Min Act: -0.1700
Data Index: 4111770 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0786. Min Range: -3.0786
Max Act: 3.0312. Min Act: -0.1700
Data Index: 2957601 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0786. Min Range: -3.0786
Max Act: 3.0312. Min Act: -0.1700
Data Index: 649061 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0786. Min Range: -3.0786
Max Act: 2.9522. Min Act: -0.1700
Data Index: 7247828 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0786. Min Range: -3.0786
Max Act: 2.9364. Min Act: -0.1700
Data Index: 5444691 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0786. Min Range: -3.0786
Max Act: 2.9364. Min Act: -0.1700
Data Index: 6665486 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0786. Min Range: -3.0786
Max Act: 2.9364. Min Act: -0.1700
Data Index: 6709181 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0786. Min Range: -3.0786
Max Act: 2.9522. Min Act: -0.1700
Data Index: 2284703 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0786. Min Range: -3.0786
Max Act: 2.9205. Min Act: -0.1700
Data Index: 7659858 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0786. Min Range: -3.0786
Max Act: 2.9205. Min Act: -0.1700
Data Index: 5540351 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0786. Min Range: -3.0786
Max Act: 2.9205. Min Act: -0.1700
Data Index: 8064659 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0786. Min Range: -3.0786
Max Act: 2.9047. Min Act: -0.1700
Data Index: 3737225 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0786. Min Range: -3.0786
Max Act: 2.8888. Min Act: -0.1700
Data Index: 687837 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0786. Min Range: -3.0786
Max Act: 2.8729. Min Act: -0.1700
Data Index: 7073466 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0786. Min Range: -3.0786
Max Act: 2.8888. Min Act: -0.1700
Data Index: 7411377 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0786. Min Range: -3.0786
Max Act: 2.8888. Min Act: -0.1700
Data Index: 8482383 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0786. Min Range: -3.0786
Max Act: 2.8729. Min Act: -0.1700
Data Index: 5285682 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0786. Min Range: -3.0786
Max Act: 2.8888. Min Act: -0.1700
Data Index: 1802388 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0786. Min Range: -3.0786
Max Act: 2.8729. Min Act: -0.1700
Data Index: 3846983 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0786. Min Range: -3.0786
Max Act: 2.8571. Min Act: -0.1700
Data Index: 1736607 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #19