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

Dataset: Open Web Text

Neuron 282 in Layer 4

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: 3.0445. Min Range: -3.0445

Max Act: 3.0445. Min Act: -0.1700

Data Index: 3467673 (Open Web Text)

Max Activating Token Index: 56

Text #1

Max Range: 3.0445. Min Range: -3.0445

Max Act: 3.0324. Min Act: -0.1700

Data Index: 4048300 (Open Web Text)

Max Activating Token Index: 221

Text #2

Max Range: 3.0445. Min Range: -3.0445

Max Act: 3.0166. Min Act: -0.1700

Data Index: 2315781 (Open Web Text)

Max Activating Token Index: 724

Text #3

Max Range: 3.0445. Min Range: -3.0445

Max Act: 3.0229. Min Act: -0.1700

Data Index: 1901206 (Open Web Text)

Max Activating Token Index: 829

Text #4

Max Range: 3.0445. Min Range: -3.0445

Max Act: 2.9571. Min Act: -0.1700

Data Index: 517000 (Open Web Text)

Max Activating Token Index: 482

Text #5

Max Range: 3.0445. Min Range: -3.0445

Max Act: 2.9974. Min Act: -0.1700

Data Index: 3971280 (Open Web Text)

Max Activating Token Index: 232

Text #6

Max Range: 3.0445. Min Range: -3.0445

Max Act: 2.9647. Min Act: -0.1700

Data Index: 2743011 (Open Web Text)

Max Activating Token Index: 4

Text #7

Max Range: 3.0445. Min Range: -3.0445

Max Act: 2.9815. Min Act: -0.1700

Data Index: 492723 (Open Web Text)

Max Activating Token Index: 232

Text #8

Max Range: 3.0445. Min Range: -3.0445

Max Act: 2.9399. Min Act: -0.1700

Data Index: 2393852 (Open Web Text)

Max Activating Token Index: 557

Text #9

Max Range: 3.0445. Min Range: -3.0445

Max Act: 2.9762. Min Act: -0.1700

Data Index: 3848545 (Open Web Text)

Max Activating Token Index: 465

Text #10

Max Range: 3.0445. Min Range: -3.0445

Max Act: 2.9693. Min Act: -0.1700

Data Index: 8159258 (Open Web Text)

Max Activating Token Index: 899

Text #11

Max Range: 3.0445. Min Range: -3.0445

Max Act: 2.9667. Min Act: -0.1700

Data Index: 1965202 (Open Web Text)

Max Activating Token Index: 627

Text #12

Max Range: 3.0445. Min Range: -3.0445

Max Act: 2.9629. Min Act: -0.1700

Data Index: 627362 (Open Web Text)

Max Activating Token Index: 411

Text #13

Max Range: 3.0445. Min Range: -3.0445

Max Act: 2.9254. Min Act: -0.1700

Data Index: 7951937 (Open Web Text)

Max Activating Token Index: 509

Text #14

Max Range: 3.0445. Min Range: -3.0445

Max Act: 2.9445. Min Act: -0.1700

Data Index: 8327442 (Open Web Text)

Max Activating Token Index: 915

Text #15

Max Range: 3.0445. Min Range: -3.0445

Max Act: 2.9573. Min Act: -0.1700

Data Index: 3285530 (Open Web Text)

Max Activating Token Index: 102

Text #16

Max Range: 3.0445. Min Range: -3.0445

Max Act: 2.9467. Min Act: -0.1700

Data Index: 5049643 (Open Web Text)

Max Activating Token Index: 691

Text #17

Max Range: 3.0445. Min Range: -3.0445

Max Act: 2.9508. Min Act: -0.1700

Data Index: 7531096 (Open Web Text)

Max Activating Token Index: 676

Text #18

Max Range: 3.0445. Min Range: -3.0445

Max Act: 2.9241. Min Act: -0.1700

Data Index: 3941550 (Open Web Text)

Max Activating Token Index: 979

Text #19

Max Range: 3.0445. Min Range: -3.0445

Max Act: 2.9462. Min Act: -0.1700

Data Index: 4466612 (Open Web Text)

Max Activating Token Index: 151