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

Dataset: Open Web Text

Neuron 1379 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: 3.7704. Min Range: -3.7704

Max Act: 3.7704. Min Act: -0.1700

Data Index: 6798190 (Open Web Text)

Max Activating Token Index: 65

Text #1

Max Range: 3.7704. Min Range: -3.7704

Max Act: 3.7361. Min Act: -0.1700

Data Index: 3537397 (Open Web Text)

Max Activating Token Index: 994

Text #2

Max Range: 3.7704. Min Range: -3.7704

Max Act: 3.7362. Min Act: -0.1700

Data Index: 1583645 (Open Web Text)

Max Activating Token Index: 414

Text #3

Max Range: 3.7704. Min Range: -3.7704

Max Act: 3.7347. Min Act: -0.1700

Data Index: 3015354 (Open Web Text)

Max Activating Token Index: 658

Text #4

Max Range: 3.7704. Min Range: -3.7704

Max Act: 3.6814. Min Act: -0.1700

Data Index: 3812599 (Open Web Text)

Max Activating Token Index: 849

Text #5

Max Range: 3.7704. Min Range: -3.7704

Max Act: 3.6819. Min Act: -0.1700

Data Index: 8552871 (Open Web Text)

Max Activating Token Index: 506

Text #6

Max Range: 3.7704. Min Range: -3.7704

Max Act: 3.7002. Min Act: -0.1700

Data Index: 3315021 (Open Web Text)

Max Activating Token Index: 560

Text #7

Max Range: 3.7704. Min Range: -3.7704

Max Act: 3.7000. Min Act: -0.1700

Data Index: 2712092 (Open Web Text)

Max Activating Token Index: 251

Text #8

Max Range: 3.7704. Min Range: -3.7704

Max Act: 3.7079. Min Act: -0.1700

Data Index: 3320307 (Open Web Text)

Max Activating Token Index: 194

Text #9

Max Range: 3.7704. Min Range: -3.7704

Max Act: 3.7009. Min Act: -0.1700

Data Index: 2159928 (Open Web Text)

Max Activating Token Index: 439

Text #10

Max Range: 3.7704. Min Range: -3.7704

Max Act: 3.6694. Min Act: -0.1700

Data Index: 7672528 (Open Web Text)

Max Activating Token Index: 82

Text #11

Max Range: 3.7704. Min Range: -3.7704

Max Act: 3.6876. Min Act: -0.1700

Data Index: 1804556 (Open Web Text)

Max Activating Token Index: 472

Text #12

Max Range: 3.7704. Min Range: -3.7704

Max Act: 3.6467. Min Act: -0.1700

Data Index: 2778915 (Open Web Text)

Max Activating Token Index: 379

Text #13

Max Range: 3.7704. Min Range: -3.7704

Max Act: 3.6534. Min Act: -0.1700

Data Index: 4250841 (Open Web Text)

Max Activating Token Index: 729

Text #14

Max Range: 3.7704. Min Range: -3.7704

Max Act: 3.6594. Min Act: -0.1700

Data Index: 5844975 (Open Web Text)

Max Activating Token Index: 786

Text #15

Max Range: 3.7704. Min Range: -3.7704

Max Act: 3.6531. Min Act: -0.1700

Data Index: 6050777 (Open Web Text)

Max Activating Token Index: 174

Text #16

Max Range: 3.7704. Min Range: -3.7704

Max Act: 3.6706. Min Act: -0.1700

Data Index: 6380418 (Open Web Text)

Max Activating Token Index: 151

Text #17

Max Range: 3.7704. Min Range: -3.7704

Max Act: 3.6428. Min Act: -0.1700

Data Index: 6480213 (Open Web Text)

Max Activating Token Index: 454

Text #18

Max Range: 3.7704. Min Range: -3.7704

Max Act: 3.6511. Min Act: -0.1700

Data Index: 6743451 (Open Web Text)

Max Activating Token Index: 453

Text #19

Max Range: 3.7704. Min Range: -3.7704

Max Act: 3.6623. Min Act: -0.1700

Data Index: 3131129 (Open Web Text)

Max Activating Token Index: 254