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

Dataset: Open Web Text

Neuron 2870 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: 3.6588. Min Range: -3.6588

Max Act: 3.6588. Min Act: -0.1700

Data Index: 3166265 (Open Web Text)

Max Activating Token Index: 138

Text #1

Max Range: 3.6588. Min Range: -3.6588

Max Act: 3.6109. Min Act: -0.1700

Data Index: 2418111 (Open Web Text)

Max Activating Token Index: 752

Text #2

Max Range: 3.6588. Min Range: -3.6588

Max Act: 3.5480. Min Act: -0.1700

Data Index: 7293590 (Open Web Text)

Max Activating Token Index: 1015

Text #3

Max Range: 3.6588. Min Range: -3.6588

Max Act: 3.5654. Min Act: -0.1700

Data Index: 6304863 (Open Web Text)

Max Activating Token Index: 432

Text #4

Max Range: 3.6588. Min Range: -3.6588

Max Act: 3.4965. Min Act: -0.1700

Data Index: 5994869 (Open Web Text)

Max Activating Token Index: 776

Text #5

Max Range: 3.6588. Min Range: -3.6588

Max Act: 3.4723. Min Act: -0.1700

Data Index: 6741380 (Open Web Text)

Max Activating Token Index: 479

Text #6

Max Range: 3.6588. Min Range: -3.6588

Max Act: 3.5056. Min Act: -0.1700

Data Index: 1642252 (Open Web Text)

Max Activating Token Index: 56

Text #7

Max Range: 3.6588. Min Range: -3.6588

Max Act: 3.5078. Min Act: -0.1700

Data Index: 3677491 (Open Web Text)

Max Activating Token Index: 344

Text #8

Max Range: 3.6588. Min Range: -3.6588

Max Act: 3.4817. Min Act: -0.1700

Data Index: 1343642 (Open Web Text)

Max Activating Token Index: 301

Text #9

Max Range: 3.6588. Min Range: -3.6588

Max Act: 3.4518. Min Act: -0.1700

Data Index: 8516030 (Open Web Text)

Max Activating Token Index: 246

Text #10

Max Range: 3.6588. Min Range: -3.6588

Max Act: 3.4446. Min Act: -0.1700

Data Index: 5915454 (Open Web Text)

Max Activating Token Index: 318

Text #11

Max Range: 3.6588. Min Range: -3.6588

Max Act: 3.4592. Min Act: -0.1700

Data Index: 5648590 (Open Web Text)

Max Activating Token Index: 501

Text #12

Max Range: 3.6588. Min Range: -3.6588

Max Act: 3.4737. Min Act: -0.1700

Data Index: 4636497 (Open Web Text)

Max Activating Token Index: 190

Text #13

Max Range: 3.6588. Min Range: -3.6588

Max Act: 3.4698. Min Act: -0.1700

Data Index: 7481231 (Open Web Text)

Max Activating Token Index: 683

Text #14

Max Range: 3.6588. Min Range: -3.6588

Max Act: 3.4731. Min Act: -0.1700

Data Index: 4312389 (Open Web Text)

Max Activating Token Index: 983

Text #15

Max Range: 3.6588. Min Range: -3.6588

Max Act: 3.4553. Min Act: -0.1700

Data Index: 3247673 (Open Web Text)

Max Activating Token Index: 53

Text #16

Max Range: 3.6588. Min Range: -3.6588

Max Act: 3.4472. Min Act: -0.1700

Data Index: 6826904 (Open Web Text)

Max Activating Token Index: 48

Text #17

Max Range: 3.6588. Min Range: -3.6588

Max Act: 3.4106. Min Act: -0.1700

Data Index: 3649032 (Open Web Text)

Max Activating Token Index: 275

Text #18

Max Range: 3.6588. Min Range: -3.6588

Max Act: 3.4319. Min Act: -0.1700

Data Index: 2347370 (Open Web Text)

Max Activating Token Index: 853

Text #19

Max Range: 3.6588. Min Range: -3.6588

Max Act: 3.4442. Min Act: -0.1700

Data Index: 2467550 (Open Web Text)

Max Activating Token Index: 138