Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 246 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.6796. Min Range: -4.6796
Max Act: 4.6796. Min Act: -0.1700
Data Index: 446221 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6796. Min Range: -4.6796
Max Act: 4.5859. Min Act: -0.1700
Data Index: 6099087 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6796. Min Range: -4.6796
Max Act: 4.5234. Min Act: -0.1700
Data Index: 3439865 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6796. Min Range: -4.6796
Max Act: 4.5234. Min Act: -0.1700
Data Index: 1446525 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6796. Min Range: -4.6796
Max Act: 4.4921. Min Act: -0.1700
Data Index: 4414021 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6796. Min Range: -4.6796
Max Act: 4.4609. Min Act: -0.1700
Data Index: 7720949 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6796. Min Range: -4.6796
Max Act: 4.4609. Min Act: -0.1700
Data Index: 6715028 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6796. Min Range: -4.6796
Max Act: 4.4609. Min Act: -0.1700
Data Index: 3166645 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6796. Min Range: -4.6796
Max Act: 4.3984. Min Act: -0.1700
Data Index: 3770662 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6796. Min Range: -4.6796
Max Act: 4.4609. Min Act: -0.1700
Data Index: 1117993 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6796. Min Range: -4.6796
Max Act: 4.4296. Min Act: -0.1700
Data Index: 6843723 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6796. Min Range: -4.6796
Max Act: 4.4609. Min Act: -0.1700
Data Index: 1102002 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6796. Min Range: -4.6796
Max Act: 4.4296. Min Act: -0.1700
Data Index: 4072629 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6796. Min Range: -4.6796
Max Act: 4.3984. Min Act: -0.1700
Data Index: 8284869 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6796. Min Range: -4.6796
Max Act: 4.3984. Min Act: -0.1700
Data Index: 7925138 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6796. Min Range: -4.6796
Max Act: 4.3671. Min Act: -0.1700
Data Index: 6216312 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6796. Min Range: -4.6796
Max Act: 4.3671. Min Act: -0.1700
Data Index: 1970745 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6796. Min Range: -4.6796
Max Act: 4.3671. Min Act: -0.1700
Data Index: 2880116 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6796. Min Range: -4.6796
Max Act: 4.3671. Min Act: -0.1700
Data Index: 6344953 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6796. Min Range: -4.6796
Max Act: 4.3671. Min Act: -0.1700
Data Index: 7648700 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #19