Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1499 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.0773. Min Range: -4.0773
Max Act: 4.0461. Min Act: -0.1700
Data Index: 8114485 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0773. Min Range: -4.0773
Max Act: 4.0773. Min Act: -0.1700
Data Index: 2096057 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0773. Min Range: -4.0773
Max Act: 3.9210. Min Act: -0.1700
Data Index: 5719613 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0773. Min Range: -4.0773
Max Act: 3.8741. Min Act: -0.1700
Data Index: 8025232 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0773. Min Range: -4.0773
Max Act: 3.8429. Min Act: -0.1700
Data Index: 7068844 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0773. Min Range: -4.0773
Max Act: 3.8429. Min Act: -0.1700
Data Index: 4863735 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0773. Min Range: -4.0773
Max Act: 3.8116. Min Act: -0.1700
Data Index: 7378118 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0773. Min Range: -4.0773
Max Act: 3.7803. Min Act: -0.1700
Data Index: 8674672 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0773. Min Range: -4.0773
Max Act: 3.7959. Min Act: -0.1700
Data Index: 8535874 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0773. Min Range: -4.0773
Max Act: 3.7803. Min Act: -0.1700
Data Index: 1892956 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0773. Min Range: -4.0773
Max Act: 3.7647. Min Act: -0.1700
Data Index: 3339250 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0773. Min Range: -4.0773
Max Act: 3.7959. Min Act: -0.1700
Data Index: 4649483 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0773. Min Range: -4.0773
Max Act: 3.7647. Min Act: -0.1700
Data Index: 6130681 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0773. Min Range: -4.0773
Max Act: 3.7803. Min Act: -0.1700
Data Index: 4074423 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0773. Min Range: -4.0773
Max Act: 3.7647. Min Act: -0.1700
Data Index: 3813701 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0773. Min Range: -4.0773
Max Act: 3.7490. Min Act: -0.1700
Data Index: 1211054 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0773. Min Range: -4.0773
Max Act: 3.7334. Min Act: -0.1700
Data Index: 5899438 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0773. Min Range: -4.0773
Max Act: 3.7334. Min Act: -0.1700
Data Index: 3443801 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0773. Min Range: -4.0773
Max Act: 3.7334. Min Act: -0.1700
Data Index: 5047001 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0773. Min Range: -4.0773
Max Act: 3.7178. Min Act: -0.1700
Data Index: 7071051 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #19