Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3542 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.7293. Min Range: -6.7293
Max Act: 6.7293. Min Act: -0.1700
Data Index: 336638 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7293. Min Range: -6.7293
Max Act: 6.6356. Min Act: -0.1700
Data Index: 5488575 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7293. Min Range: -6.7293
Max Act: 6.5418. Min Act: -0.1700
Data Index: 28263 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7293. Min Range: -6.7293
Max Act: 6.5731. Min Act: -0.1700
Data Index: 2718832 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7293. Min Range: -6.7293
Max Act: 6.5106. Min Act: -0.1700
Data Index: 4604098 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7293. Min Range: -6.7293
Max Act: 6.4168. Min Act: -0.1700
Data Index: 5067036 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7293. Min Range: -6.7293
Max Act: 6.4168. Min Act: -0.1700
Data Index: 3972133 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7293. Min Range: -6.7293
Max Act: 6.4168. Min Act: -0.1700
Data Index: 7970140 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7293. Min Range: -6.7293
Max Act: 6.4168. Min Act: -0.1700
Data Index: 6171426 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7293. Min Range: -6.7293
Max Act: 6.3856. Min Act: -0.1700
Data Index: 8038833 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7293. Min Range: -6.7293
Max Act: 6.3543. Min Act: -0.1700
Data Index: 6269427 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7293. Min Range: -6.7293
Max Act: 6.2606. Min Act: -0.1700
Data Index: 5488576 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7293. Min Range: -6.7293
Max Act: 6.3231. Min Act: -0.1700
Data Index: 7235424 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7293. Min Range: -6.7293
Max Act: 6.2606. Min Act: -0.1700
Data Index: 515857 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7293. Min Range: -6.7293
Max Act: 6.2293. Min Act: -0.1700
Data Index: 1536044 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7293. Min Range: -6.7293
Max Act: 6.2293. Min Act: -0.1700
Data Index: 779356 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7293. Min Range: -6.7293
Max Act: 6.1668. Min Act: -0.1700
Data Index: 6160067 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7293. Min Range: -6.7293
Max Act: 6.1981. Min Act: -0.1700
Data Index: 4792767 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7293. Min Range: -6.7293
Max Act: 6.1356. Min Act: -0.1700
Data Index: 1177525 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7293. Min Range: -6.7293
Max Act: 6.1668. Min Act: -0.1700
Data Index: 2685557 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #19