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

Dataset: Open Web Text

Neuron 337 in Layer 1

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: 1.3729. Min Range: -1.3729

Max Act: 1.3729. Min Act: -0.1700

Data Index: 1751456 (Open Web Text)

Max Activating Token Index: 92

Text #1

Max Range: 1.3729. Min Range: -1.3729

Max Act: 1.3573. Min Act: -0.1699

Data Index: 7432125 (Open Web Text)

Max Activating Token Index: 136

Text #2

Max Range: 1.3729. Min Range: -1.3729

Max Act: 1.3601. Min Act: -0.1625

Data Index: 6772499 (Open Web Text)

Max Activating Token Index: 153

Text #3

Max Range: 1.3729. Min Range: -1.3729

Max Act: 1.3580. Min Act: -0.1696

Data Index: 1436750 (Open Web Text)

Max Activating Token Index: 142

Text #4

Max Range: 1.3729. Min Range: -1.3729

Max Act: 1.3569. Min Act: -0.1695

Data Index: 5985869 (Open Web Text)

Max Activating Token Index: 76

Text #5

Max Range: 1.3729. Min Range: -1.3729

Max Act: 1.3553. Min Act: -0.1700

Data Index: 5810381 (Open Web Text)

Max Activating Token Index: 131

Text #6

Max Range: 1.3729. Min Range: -1.3729

Max Act: 1.3502. Min Act: -0.1700

Data Index: 901968 (Open Web Text)

Max Activating Token Index: 659

Text #7

Max Range: 1.3729. Min Range: -1.3729

Max Act: 1.3538. Min Act: -0.1696

Data Index: 334344 (Open Web Text)

Max Activating Token Index: 688

Text #8

Max Range: 1.3729. Min Range: -1.3729

Max Act: 1.3508. Min Act: -0.1674

Data Index: 8207724 (Open Web Text)

Max Activating Token Index: 200

Text #9

Max Range: 1.3729. Min Range: -1.3729

Max Act: 1.3464. Min Act: -0.1700

Data Index: 5499980 (Open Web Text)

Max Activating Token Index: 201

Text #10

Max Range: 1.3729. Min Range: -1.3729

Max Act: 1.3433. Min Act: -0.1690

Data Index: 5833470 (Open Web Text)

Max Activating Token Index: 125

Text #11

Max Range: 1.3729. Min Range: -1.3729

Max Act: 1.3385. Min Act: -0.1700

Data Index: 2688199 (Open Web Text)

Max Activating Token Index: 689

Text #12

Max Range: 1.3729. Min Range: -1.3729

Max Act: 1.3406. Min Act: -0.1612

Data Index: 7064831 (Open Web Text)

Max Activating Token Index: 176

Text #13

Max Range: 1.3729. Min Range: -1.3729

Max Act: 1.3413. Min Act: -0.1694

Data Index: 8568724 (Open Web Text)

Max Activating Token Index: 436

Text #14

Max Range: 1.3729. Min Range: -1.3729

Max Act: 1.3412. Min Act: -0.1698

Data Index: 7403687 (Open Web Text)

Max Activating Token Index: 460

Text #15

Max Range: 1.3729. Min Range: -1.3729

Max Act: 1.3333. Min Act: -0.1699

Data Index: 4914173 (Open Web Text)

Max Activating Token Index: 182

Text #16

Max Range: 1.3729. Min Range: -1.3729

Max Act: 1.3423. Min Act: -0.1639

Data Index: 7695250 (Open Web Text)

Max Activating Token Index: 177

Text #17

Max Range: 1.3729. Min Range: -1.3729

Max Act: 1.3444. Min Act: -0.1657

Data Index: 7594545 (Open Web Text)

Max Activating Token Index: 618

Text #18

Max Range: 1.3729. Min Range: -1.3729

Max Act: 1.3394. Min Act: -0.1684

Data Index: 719920 (Open Web Text)

Max Activating Token Index: 200

Text #19

Max Range: 1.3729. Min Range: -1.3729

Max Act: 1.3324. Min Act: -0.1626

Data Index: 3959835 (Open Web Text)

Max Activating Token Index: 275