Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2054 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.9013. Min Range: -3.9013
Max Act: 3.9013. Min Act: -0.1700
Data Index: 7651678 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9013. Min Range: -3.9013
Max Act: 3.7762. Min Act: -0.1700
Data Index: 2487376 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9013. Min Range: -3.9013
Max Act: 3.8075. Min Act: -0.1700
Data Index: 4743178 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9013. Min Range: -3.9013
Max Act: 3.7293. Min Act: -0.1700
Data Index: 4858680 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9013. Min Range: -3.9013
Max Act: 3.7449. Min Act: -0.1700
Data Index: 479298 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9013. Min Range: -3.9013
Max Act: 3.7293. Min Act: -0.1700
Data Index: 2685985 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9013. Min Range: -3.9013
Max Act: 3.7136. Min Act: -0.1700
Data Index: 3327049 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9013. Min Range: -3.9013
Max Act: 3.6824. Min Act: -0.1700
Data Index: 7901731 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9013. Min Range: -3.9013
Max Act: 3.6980. Min Act: -0.1700
Data Index: 3603360 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9013. Min Range: -3.9013
Max Act: 3.6824. Min Act: -0.1700
Data Index: 8555101 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9013. Min Range: -3.9013
Max Act: 3.6667. Min Act: -0.1700
Data Index: 8091904 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9013. Min Range: -3.9013
Max Act: 3.6667. Min Act: -0.1700
Data Index: 3839041 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9013. Min Range: -3.9013
Max Act: 3.6511. Min Act: -0.1700
Data Index: 5313242 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9013. Min Range: -3.9013
Max Act: 3.6354. Min Act: -0.1700
Data Index: 6562225 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9013. Min Range: -3.9013
Max Act: 3.6198. Min Act: -0.1700
Data Index: 1679843 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9013. Min Range: -3.9013
Max Act: 3.6354. Min Act: -0.1700
Data Index: 2608878 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9013. Min Range: -3.9013
Max Act: 3.6511. Min Act: -0.1700
Data Index: 5272972 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9013. Min Range: -3.9013
Max Act: 3.6354. Min Act: -0.1700
Data Index: 1814865 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9013. Min Range: -3.9013
Max Act: 3.6198. Min Act: -0.1700
Data Index: 8787885 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9013. Min Range: -3.9013
Max Act: 3.6041. Min Act: -0.1700
Data Index: 1585346 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19