Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2984 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.5027. Min Range: -1.5027
Max Act: 1.5027. Min Act: -0.1700
Data Index: 1912475 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.5027. Min Range: -1.5027
Max Act: 1.4499. Min Act: -0.1700
Data Index: 1484532 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.5027. Min Range: -1.5027
Max Act: 1.4235. Min Act: -0.1700
Data Index: 5957079 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.5027. Min Range: -1.5027
Max Act: 1.4147. Min Act: -0.1700
Data Index: 3491965 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.5027. Min Range: -1.5027
Max Act: 1.4059. Min Act: -0.1700
Data Index: 4547521 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.5027. Min Range: -1.5027
Max Act: 1.4059. Min Act: -0.1700
Data Index: 4736004 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.5027. Min Range: -1.5027
Max Act: 1.3971. Min Act: -0.1700
Data Index: 3771394 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.5027. Min Range: -1.5027
Max Act: 1.4059. Min Act: -0.1700
Data Index: 1522290 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.5027. Min Range: -1.5027
Max Act: 1.3971. Min Act: -0.1700
Data Index: 2534816 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.5027. Min Range: -1.5027
Max Act: 1.3795. Min Act: -0.1700
Data Index: 4895774 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.5027. Min Range: -1.5027
Max Act: 1.3707. Min Act: -0.1700
Data Index: 8816621 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.5027. Min Range: -1.5027
Max Act: 1.3618. Min Act: -0.1700
Data Index: 8769575 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.5027. Min Range: -1.5027
Max Act: 1.3442. Min Act: -0.1700
Data Index: 2009443 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.5027. Min Range: -1.5027
Max Act: 1.3354. Min Act: -0.1700
Data Index: 3802417 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.5027. Min Range: -1.5027
Max Act: 1.3354. Min Act: -0.1700
Data Index: 2897217 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.5027. Min Range: -1.5027
Max Act: 1.3177. Min Act: -0.1700
Data Index: 80426 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.5027. Min Range: -1.5027
Max Act: 1.3266. Min Act: -0.1700
Data Index: 1056692 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.5027. Min Range: -1.5027
Max Act: 1.3354. Min Act: -0.1700
Data Index: 5077099 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.5027. Min Range: -1.5027
Max Act: 1.3089. Min Act: -0.1700
Data Index: 6498018 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.5027. Min Range: -1.5027
Max Act: 1.3089. Min Act: -0.1700
Data Index: 4668097 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #19