Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2722 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.6953. Min Range: -1.6953
Max Act: 1.6953. Min Act: -0.1700
Data Index: 4449563 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.6953. Min Range: -1.6953
Max Act: 1.6692. Min Act: -0.1700
Data Index: 4920 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.6953. Min Range: -1.6953
Max Act: 1.6692. Min Act: -0.1700
Data Index: 1152475 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.6953. Min Range: -1.6953
Max Act: 1.6779. Min Act: -0.1700
Data Index: 6552825 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.6953. Min Range: -1.6953
Max Act: 1.6519. Min Act: -0.1700
Data Index: 4820704 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.6953. Min Range: -1.6953
Max Act: 1.6606. Min Act: -0.1700
Data Index: 642994 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.6953. Min Range: -1.6953
Max Act: 1.6606. Min Act: -0.1700
Data Index: 3530006 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.6953. Min Range: -1.6953
Max Act: 1.6432. Min Act: -0.1700
Data Index: 5503325 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.6953. Min Range: -1.6953
Max Act: 1.6519. Min Act: -0.1700
Data Index: 5213337 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.6953. Min Range: -1.6953
Max Act: 1.6432. Min Act: -0.1700
Data Index: 8269321 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.6953. Min Range: -1.6953
Max Act: 1.6606. Min Act: -0.1700
Data Index: 2427735 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.6953. Min Range: -1.6953
Max Act: 1.6432. Min Act: -0.1700
Data Index: 2845947 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.6953. Min Range: -1.6953
Max Act: 1.6257. Min Act: -0.1700
Data Index: 129691 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.6953. Min Range: -1.6953
Max Act: 1.6257. Min Act: -0.1700
Data Index: 3968700 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.6953. Min Range: -1.6953
Max Act: 1.6432. Min Act: -0.1700
Data Index: 2203890 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.6953. Min Range: -1.6953
Max Act: 1.6257. Min Act: -0.1700
Data Index: 6217603 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.6953. Min Range: -1.6953
Max Act: 1.6257. Min Act: -0.1700
Data Index: 3159265 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.6953. Min Range: -1.6953
Max Act: 1.6257. Min Act: -0.1700
Data Index: 2422021 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.6953. Min Range: -1.6953
Max Act: 1.6170. Min Act: -0.1700
Data Index: 5745227 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.6953. Min Range: -1.6953
Max Act: 1.6344. Min Act: -0.1700
Data Index: 7665099 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #19