Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1404 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.1194. Min Range: -4.1194
Max Act: 4.1194. Min Act: -0.1700
Data Index: 1896930 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1194. Min Range: -4.1194
Max Act: 4.1194. Min Act: -0.1700
Data Index: 1268910 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1194. Min Range: -4.1194
Max Act: 3.9631. Min Act: -0.1700
Data Index: 5743891 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1194. Min Range: -4.1194
Max Act: 3.9006. Min Act: -0.1700
Data Index: 8663553 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1194. Min Range: -4.1194
Max Act: 3.9006. Min Act: -0.1700
Data Index: 1368 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1194. Min Range: -4.1194
Max Act: 3.8380. Min Act: -0.1700
Data Index: 1896928 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1194. Min Range: -4.1194
Max Act: 3.8693. Min Act: -0.1700
Data Index: 7195167 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1194. Min Range: -4.1194
Max Act: 3.8067. Min Act: -0.1700
Data Index: 8216473 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1194. Min Range: -4.1194
Max Act: 3.8693. Min Act: -0.1700
Data Index: 264513 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1194. Min Range: -4.1194
Max Act: 3.8380. Min Act: -0.1700
Data Index: 5975880 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1194. Min Range: -4.1194
Max Act: 3.8067. Min Act: -0.1700
Data Index: 508677 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1194. Min Range: -4.1194
Max Act: 3.8067. Min Act: -0.1700
Data Index: 751921 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1194. Min Range: -4.1194
Max Act: 3.8067. Min Act: -0.1700
Data Index: 5252146 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1194. Min Range: -4.1194
Max Act: 3.8067. Min Act: -0.1700
Data Index: 527599 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1194. Min Range: -4.1194
Max Act: 3.8067. Min Act: -0.1700
Data Index: 5794891 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1194. Min Range: -4.1194
Max Act: 3.7598. Min Act: -0.1700
Data Index: 4620824 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1194. Min Range: -4.1194
Max Act: 3.7755. Min Act: -0.1700
Data Index: 1875534 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1194. Min Range: -4.1194
Max Act: 3.7286. Min Act: -0.1700
Data Index: 5312951 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1194. Min Range: -4.1194
Max Act: 3.8067. Min Act: -0.1700
Data Index: 3033605 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1194. Min Range: -4.1194
Max Act: 3.7598. Min Act: -0.1700
Data Index: 2600725 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #19