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

Dataset: Open Web Text

Neuron 1602 in Layer 2

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: 4.3385. Min Range: -4.3385

Max Act: 4.3385. Min Act: -0.1700

Data Index: 2878879 (Open Web Text)

Max Activating Token Index: 191

Text #1

Max Range: 4.3385. Min Range: -4.3385

Max Act: 4.2030. Min Act: -0.1700

Data Index: 6337545 (Open Web Text)

Max Activating Token Index: 99

Text #2

Max Range: 4.3385. Min Range: -4.3385

Max Act: 4.1593. Min Act: -0.1700

Data Index: 4080043 (Open Web Text)

Max Activating Token Index: 34

Text #3

Max Range: 4.3385. Min Range: -4.3385

Max Act: 4.1445. Min Act: -0.1700

Data Index: 2348060 (Open Web Text)

Max Activating Token Index: 983

Text #4

Max Range: 4.3385. Min Range: -4.3385

Max Act: 4.1257. Min Act: -0.1700

Data Index: 1760399 (Open Web Text)

Max Activating Token Index: 647

Text #5

Max Range: 4.3385. Min Range: -4.3385

Max Act: 4.0762. Min Act: -0.1700

Data Index: 896564 (Open Web Text)

Max Activating Token Index: 35

Text #6

Max Range: 4.3385. Min Range: -4.3385

Max Act: 4.0912. Min Act: -0.1700

Data Index: 942414 (Open Web Text)

Max Activating Token Index: 58

Text #7

Max Range: 4.3385. Min Range: -4.3385

Max Act: 4.0847. Min Act: -0.1700

Data Index: 4816427 (Open Web Text)

Max Activating Token Index: 287

Text #8

Max Range: 4.3385. Min Range: -4.3385

Max Act: 4.0607. Min Act: -0.1700

Data Index: 6316076 (Open Web Text)

Max Activating Token Index: 401

Text #9

Max Range: 4.3385. Min Range: -4.3385

Max Act: 4.0530. Min Act: -0.1700

Data Index: 7128193 (Open Web Text)

Max Activating Token Index: 12

Text #10

Max Range: 4.3385. Min Range: -4.3385

Max Act: 4.0614. Min Act: -0.1700

Data Index: 2878486 (Open Web Text)

Max Activating Token Index: 686

Text #11

Max Range: 4.3385. Min Range: -4.3385

Max Act: 4.0317. Min Act: -0.1700

Data Index: 3385676 (Open Web Text)

Max Activating Token Index: 613

Text #12

Max Range: 4.3385. Min Range: -4.3385

Max Act: 4.0029. Min Act: -0.1700

Data Index: 1294674 (Open Web Text)

Max Activating Token Index: 176

Text #13

Max Range: 4.3385. Min Range: -4.3385

Max Act: 3.9898. Min Act: -0.1700

Data Index: 5181939 (Open Web Text)

Max Activating Token Index: 41

Text #14

Max Range: 4.3385. Min Range: -4.3385

Max Act: 3.9729. Min Act: -0.1700

Data Index: 702983 (Open Web Text)

Max Activating Token Index: 426

Text #15

Max Range: 4.3385. Min Range: -4.3385

Max Act: 3.9960. Min Act: -0.1700

Data Index: 7471187 (Open Web Text)

Max Activating Token Index: 677

Text #16

Max Range: 4.3385. Min Range: -4.3385

Max Act: 3.9436. Min Act: -0.1700

Data Index: 781639 (Open Web Text)

Max Activating Token Index: 5

Text #17

Max Range: 4.3385. Min Range: -4.3385

Max Act: 3.9602. Min Act: -0.1700

Data Index: 3219449 (Open Web Text)

Max Activating Token Index: 583

Text #18

Max Range: 4.3385. Min Range: -4.3385

Max Act: 3.9453. Min Act: -0.1700

Data Index: 525605 (Open Web Text)

Max Activating Token Index: 844

Text #19

Max Range: 4.3385. Min Range: -4.3385

Max Act: 3.9184. Min Act: -0.1700

Data Index: 5469692 (Open Web Text)

Max Activating Token Index: 333