Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 2677 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')

Click the toggle to see the full text!

Text #0

Max Range: 3.6189. Min Range: -3.6189

Max Act: 3.6189. Min Act: -0.1700

Data Index: 1199565 (Open Web Text)

Max Activating Token Index: 847

Text #1

Max Range: 3.6189. Min Range: -3.6189

Max Act: 3.6052. Min Act: -0.1700

Data Index: 5466275 (Open Web Text)

Max Activating Token Index: 709

Text #2

Max Range: 3.6189. Min Range: -3.6189

Max Act: 3.5901. Min Act: -0.1700

Data Index: 4358334 (Open Web Text)

Max Activating Token Index: 311

Text #3

Max Range: 3.6189. Min Range: -3.6189

Max Act: 3.5470. Min Act: -0.1700

Data Index: 1701550 (Open Web Text)

Max Activating Token Index: 527

Text #4

Max Range: 3.6189. Min Range: -3.6189

Max Act: 3.5178. Min Act: -0.1700

Data Index: 5116589 (Open Web Text)

Max Activating Token Index: 196

Text #5

Max Range: 3.6189. Min Range: -3.6189

Max Act: 3.5080. Min Act: -0.1700

Data Index: 418686 (Open Web Text)

Max Activating Token Index: 608

Text #6

Max Range: 3.6189. Min Range: -3.6189

Max Act: 3.5219. Min Act: -0.1700

Data Index: 4362011 (Open Web Text)

Max Activating Token Index: 881

Text #7

Max Range: 3.6189. Min Range: -3.6189

Max Act: 3.5089. Min Act: -0.1700

Data Index: 8305750 (Open Web Text)

Max Activating Token Index: 1018

Text #8

Max Range: 3.6189. Min Range: -3.6189

Max Act: 3.4853. Min Act: -0.1700

Data Index: 5766232 (Open Web Text)

Max Activating Token Index: 677

Text #9

Max Range: 3.6189. Min Range: -3.6189

Max Act: 3.4890. Min Act: -0.1700

Data Index: 2510272 (Open Web Text)

Max Activating Token Index: 1021

Text #10

Max Range: 3.6189. Min Range: -3.6189

Max Act: 3.4525. Min Act: -0.1700

Data Index: 1898956 (Open Web Text)

Max Activating Token Index: 189

Text #11

Max Range: 3.6189. Min Range: -3.6189

Max Act: 3.4229. Min Act: -0.1700

Data Index: 5664337 (Open Web Text)

Max Activating Token Index: 414

Text #12

Max Range: 3.6189. Min Range: -3.6189

Max Act: 3.4293. Min Act: -0.1700

Data Index: 5454915 (Open Web Text)

Max Activating Token Index: 229

Text #13

Max Range: 3.6189. Min Range: -3.6189

Max Act: 3.4454. Min Act: -0.1700

Data Index: 1840977 (Open Web Text)

Max Activating Token Index: 93

Text #14

Max Range: 3.6189. Min Range: -3.6189

Max Act: 3.4214. Min Act: -0.1700

Data Index: 2416916 (Open Web Text)

Max Activating Token Index: 884

Text #15

Max Range: 3.6189. Min Range: -3.6189

Max Act: 3.4051. Min Act: -0.1700

Data Index: 2744568 (Open Web Text)

Max Activating Token Index: 515

Text #16

Max Range: 3.6189. Min Range: -3.6189

Max Act: 3.3892. Min Act: -0.1700

Data Index: 3108743 (Open Web Text)

Max Activating Token Index: 595

Text #17

Max Range: 3.6189. Min Range: -3.6189

Max Act: 3.3874. Min Act: -0.1700

Data Index: 7684806 (Open Web Text)

Max Activating Token Index: 607

Text #18

Max Range: 3.6189. Min Range: -3.6189

Max Act: 3.3846. Min Act: -0.1700

Data Index: 6261308 (Open Web Text)

Max Activating Token Index: 19

Text #19

Max Range: 3.6189. Min Range: -3.6189

Max Act: 3.3723. Min Act: -0.1700

Data Index: 2151471 (Open Web Text)

Max Activating Token Index: 551