Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1333 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.2194. Min Range: -4.2194
Max Act: 4.2194. Min Act: -0.1700
Data Index: 6854274 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2194. Min Range: -4.2194
Max Act: 4.2194. Min Act: -0.1700
Data Index: 234780 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2194. Min Range: -4.2194
Max Act: 4.0944. Min Act: -0.1700
Data Index: 2723260 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2194. Min Range: -4.2194
Max Act: 4.0318. Min Act: -0.1700
Data Index: 4804899 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2194. Min Range: -4.2194
Max Act: 4.0631. Min Act: -0.1700
Data Index: 624551 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2194. Min Range: -4.2194
Max Act: 4.0318. Min Act: -0.1700
Data Index: 5096109 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2194. Min Range: -4.2194
Max Act: 3.9693. Min Act: -0.1700
Data Index: 2879305 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2194. Min Range: -4.2194
Max Act: 3.9693. Min Act: -0.1700
Data Index: 4122937 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2194. Min Range: -4.2194
Max Act: 3.9068. Min Act: -0.1700
Data Index: 6069751 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2194. Min Range: -4.2194
Max Act: 3.9068. Min Act: -0.1700
Data Index: 8386984 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2194. Min Range: -4.2194
Max Act: 3.9068. Min Act: -0.1700
Data Index: 87275 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2194. Min Range: -4.2194
Max Act: 3.9068. Min Act: -0.1700
Data Index: 7621671 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2194. Min Range: -4.2194
Max Act: 3.8755. Min Act: -0.1700
Data Index: 5097173 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2194. Min Range: -4.2194
Max Act: 3.8443. Min Act: -0.1700
Data Index: 4673871 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2194. Min Range: -4.2194
Max Act: 3.9068. Min Act: -0.1700
Data Index: 2777395 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2194. Min Range: -4.2194
Max Act: 3.8755. Min Act: -0.1700
Data Index: 2141263 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2194. Min Range: -4.2194
Max Act: 3.8755. Min Act: -0.1700
Data Index: 6971893 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2194. Min Range: -4.2194
Max Act: 3.8755. Min Act: -0.1700
Data Index: 3965059 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2194. Min Range: -4.2194
Max Act: 3.8755. Min Act: -0.1700
Data Index: 5386919 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2194. Min Range: -4.2194
Max Act: 3.8755. Min Act: -0.1700
Data Index: 835783 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #19