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

Dataset: Open Web Text

Neuron 1152 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: 3.0310. Min Range: -3.0310

Max Act: 3.0310. Min Act: -0.1700

Data Index: 6575292 (Open Web Text)

Max Activating Token Index: 685

Text #1

Max Range: 3.0310. Min Range: -3.0310

Max Act: 3.0104. Min Act: -0.1700

Data Index: 3643187 (Open Web Text)

Max Activating Token Index: 792

Text #2

Max Range: 3.0310. Min Range: -3.0310

Max Act: 3.0158. Min Act: -0.1700

Data Index: 1940644 (Open Web Text)

Max Activating Token Index: 591

Text #3

Max Range: 3.0310. Min Range: -3.0310

Max Act: 2.9671. Min Act: -0.1700

Data Index: 2584043 (Open Web Text)

Max Activating Token Index: 521

Text #4

Max Range: 3.0310. Min Range: -3.0310

Max Act: 2.9873. Min Act: -0.1700

Data Index: 6689241 (Open Web Text)

Max Activating Token Index: 1022

Text #5

Max Range: 3.0310. Min Range: -3.0310

Max Act: 2.9573. Min Act: -0.1700

Data Index: 5932546 (Open Web Text)

Max Activating Token Index: 538

Text #6

Max Range: 3.0310. Min Range: -3.0310

Max Act: 2.9709. Min Act: -0.1700

Data Index: 4914718 (Open Web Text)

Max Activating Token Index: 584

Text #7

Max Range: 3.0310. Min Range: -3.0310

Max Act: 2.9539. Min Act: -0.1700

Data Index: 2632638 (Open Web Text)

Max Activating Token Index: 583

Text #8

Max Range: 3.0310. Min Range: -3.0310

Max Act: 2.9677. Min Act: -0.1700

Data Index: 6353516 (Open Web Text)

Max Activating Token Index: 298

Text #9

Max Range: 3.0310. Min Range: -3.0310

Max Act: 2.9629. Min Act: -0.1700

Data Index: 4743922 (Open Web Text)

Max Activating Token Index: 395

Text #10

Max Range: 3.0310. Min Range: -3.0310

Max Act: 2.9541. Min Act: -0.1700

Data Index: 4501225 (Open Web Text)

Max Activating Token Index: 944

Text #11

Max Range: 3.0310. Min Range: -3.0310

Max Act: 2.9373. Min Act: -0.1700

Data Index: 6430264 (Open Web Text)

Max Activating Token Index: 914

Text #12

Max Range: 3.0310. Min Range: -3.0310

Max Act: 2.9279. Min Act: -0.1700

Data Index: 5065311 (Open Web Text)

Max Activating Token Index: 847

Text #13

Max Range: 3.0310. Min Range: -3.0310

Max Act: 2.9390. Min Act: -0.1700

Data Index: 1185414 (Open Web Text)

Max Activating Token Index: 384

Text #14

Max Range: 3.0310. Min Range: -3.0310

Max Act: 2.9523. Min Act: -0.1700

Data Index: 6724041 (Open Web Text)

Max Activating Token Index: 989

Text #15

Max Range: 3.0310. Min Range: -3.0310

Max Act: 2.9318. Min Act: -0.1700

Data Index: 335778 (Open Web Text)

Max Activating Token Index: 992

Text #16

Max Range: 3.0310. Min Range: -3.0310

Max Act: 2.9478. Min Act: -0.1700

Data Index: 2313118 (Open Web Text)

Max Activating Token Index: 658

Text #17

Max Range: 3.0310. Min Range: -3.0310

Max Act: 2.9305. Min Act: -0.1700

Data Index: 582433 (Open Web Text)

Max Activating Token Index: 649

Text #18

Max Range: 3.0310. Min Range: -3.0310

Max Act: 2.9340. Min Act: -0.1700

Data Index: 1164010 (Open Web Text)

Max Activating Token Index: 397

Text #19

Max Range: 3.0310. Min Range: -3.0310

Max Act: 2.9418. Min Act: -0.1700

Data Index: 2437268 (Open Web Text)

Max Activating Token Index: 720