Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1224 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.9885. Min Range: -2.9885
Max Act: 2.9885. Min Act: -0.1700
Data Index: 3560933 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9885. Min Range: -2.9885
Max Act: 2.9252. Min Act: -0.1700
Data Index: 2931282 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9885. Min Range: -2.9885
Max Act: 2.9093. Min Act: -0.1700
Data Index: 4834914 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9885. Min Range: -2.9885
Max Act: 2.8935. Min Act: -0.1700
Data Index: 748945 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9885. Min Range: -2.9885
Max Act: 2.8935. Min Act: -0.1700
Data Index: 930303 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9885. Min Range: -2.9885
Max Act: 2.8140. Min Act: -0.1700
Data Index: 8395415 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9885. Min Range: -2.9885
Max Act: 2.7822. Min Act: -0.1700
Data Index: 3234034 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9885. Min Range: -2.9885
Max Act: 2.7822. Min Act: -0.1700
Data Index: 4549506 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9885. Min Range: -2.9885
Max Act: 2.7822. Min Act: -0.1700
Data Index: 4548405 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9885. Min Range: -2.9885
Max Act: 2.7662. Min Act: -0.1700
Data Index: 7407389 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9885. Min Range: -2.9885
Max Act: 2.7662. Min Act: -0.1700
Data Index: 1352247 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9885. Min Range: -2.9885
Max Act: 2.7822. Min Act: -0.1700
Data Index: 1654977 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9885. Min Range: -2.9885
Max Act: 2.7503. Min Act: -0.1700
Data Index: 182847 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9885. Min Range: -2.9885
Max Act: 2.7343. Min Act: -0.1700
Data Index: 3594826 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9885. Min Range: -2.9885
Max Act: 2.7183. Min Act: -0.1700
Data Index: 1284906 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9885. Min Range: -2.9885
Max Act: 2.7183. Min Act: -0.1700
Data Index: 730770 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9885. Min Range: -2.9885
Max Act: 2.7023. Min Act: -0.1700
Data Index: 2610929 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9885. Min Range: -2.9885
Max Act: 2.7023. Min Act: -0.1700
Data Index: 42844 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9885. Min Range: -2.9885
Max Act: 2.7183. Min Act: -0.1700
Data Index: 3823324 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9885. Min Range: -2.9885
Max Act: 2.6863. Min Act: -0.1700
Data Index: 7775229 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #19