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

Dataset: Open Web Text

Neuron 1590 in Layer 3

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: 4.4644. Min Range: -4.4644

Max Act: 4.4622. Min Act: -0.1700

Data Index: 1699743 (Open Web Text)

Max Activating Token Index: 174

Text #1

Max Range: 4.4644. Min Range: -4.4644

Max Act: 4.4644. Min Act: -0.1700

Data Index: 28399 (Open Web Text)

Max Activating Token Index: 84

Text #2

Max Range: 4.4644. Min Range: -4.4644

Max Act: 4.4245. Min Act: -0.1700

Data Index: 8772156 (Open Web Text)

Max Activating Token Index: 660

Text #3

Max Range: 4.4644. Min Range: -4.4644

Max Act: 4.3607. Min Act: -0.1700

Data Index: 1112525 (Open Web Text)

Max Activating Token Index: 441

Text #4

Max Range: 4.4644. Min Range: -4.4644

Max Act: 4.3763. Min Act: -0.1700

Data Index: 6233351 (Open Web Text)

Max Activating Token Index: 651

Text #5

Max Range: 4.4644. Min Range: -4.4644

Max Act: 4.3730. Min Act: -0.1700

Data Index: 5388702 (Open Web Text)

Max Activating Token Index: 537

Text #6

Max Range: 4.4644. Min Range: -4.4644

Max Act: 4.4195. Min Act: -0.1700

Data Index: 6273988 (Open Web Text)

Max Activating Token Index: 704

Text #7

Max Range: 4.4644. Min Range: -4.4644

Max Act: 4.4006. Min Act: -0.1700

Data Index: 6843336 (Open Web Text)

Max Activating Token Index: 749

Text #8

Max Range: 4.4644. Min Range: -4.4644

Max Act: 4.4168. Min Act: -0.1700

Data Index: 2180570 (Open Web Text)

Max Activating Token Index: 628

Text #9

Max Range: 4.4644. Min Range: -4.4644

Max Act: 4.3727. Min Act: -0.1700

Data Index: 1090404 (Open Web Text)

Max Activating Token Index: 412

Text #10

Max Range: 4.4644. Min Range: -4.4644

Max Act: 4.3085. Min Act: -0.1700

Data Index: 8683428 (Open Web Text)

Max Activating Token Index: 599

Text #11

Max Range: 4.4644. Min Range: -4.4644

Max Act: 4.3959. Min Act: -0.1700

Data Index: 6124400 (Open Web Text)

Max Activating Token Index: 909

Text #12

Max Range: 4.4644. Min Range: -4.4644

Max Act: 4.3579. Min Act: -0.1700

Data Index: 5127414 (Open Web Text)

Max Activating Token Index: 291

Text #13

Max Range: 4.4644. Min Range: -4.4644

Max Act: 4.3800. Min Act: -0.1700

Data Index: 7349601 (Open Web Text)

Max Activating Token Index: 180

Text #14

Max Range: 4.4644. Min Range: -4.4644

Max Act: 4.3731. Min Act: -0.1700

Data Index: 4534973 (Open Web Text)

Max Activating Token Index: 447

Text #15

Max Range: 4.4644. Min Range: -4.4644

Max Act: 4.3353. Min Act: -0.1700

Data Index: 6946174 (Open Web Text)

Max Activating Token Index: 247

Text #16

Max Range: 4.4644. Min Range: -4.4644

Max Act: 4.3214. Min Act: -0.1700

Data Index: 2666924 (Open Web Text)

Max Activating Token Index: 1021

Text #17

Max Range: 4.4644. Min Range: -4.4644

Max Act: 4.3119. Min Act: -0.1700

Data Index: 4312187 (Open Web Text)

Max Activating Token Index: 165

Text #18

Max Range: 4.4644. Min Range: -4.4644

Max Act: 4.4293. Min Act: -0.1700

Data Index: 2105246 (Open Web Text)

Max Activating Token Index: 606

Text #19

Max Range: 4.4644. Min Range: -4.4644

Max Act: 4.3438. Min Act: -0.1700

Data Index: 397973 (Open Web Text)

Max Activating Token Index: 409