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

Dataset: Open Web Text

Neuron 1095 in Layer 0

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: 1.4358. Min Range: -1.4358

Max Act: 1.4347. Min Act: -0.0818

Data Index: 2049727 (Open Web Text)

Max Activating Token Index: 1011

Text #1

Max Range: 1.4358. Min Range: -1.4358

Max Act: 1.4358. Min Act: -0.0990

Data Index: 7683532 (Open Web Text)

Max Activating Token Index: 1015

Text #2

Max Range: 1.4358. Min Range: -1.4358

Max Act: 1.3897. Min Act: -0.1555

Data Index: 3332654 (Open Web Text)

Max Activating Token Index: 726

Text #3

Max Range: 1.4358. Min Range: -1.4358

Max Act: 1.3848. Min Act: -0.0895

Data Index: 8738764 (Open Web Text)

Max Activating Token Index: 1021

Text #4

Max Range: 1.4358. Min Range: -1.4358

Max Act: 1.3783. Min Act: -0.1153

Data Index: 6699414 (Open Web Text)

Max Activating Token Index: 780

Text #5

Max Range: 1.4358. Min Range: -1.4358

Max Act: 1.3790. Min Act: -0.0657

Data Index: 6854469 (Open Web Text)

Max Activating Token Index: 743

Text #6

Max Range: 1.4358. Min Range: -1.4358

Max Act: 1.3775. Min Act: -0.0431

Data Index: 8820500 (Open Web Text)

Max Activating Token Index: 514

Text #7

Max Range: 1.4358. Min Range: -1.4358

Max Act: 1.3715. Min Act: -0.0826

Data Index: 2228606 (Open Web Text)

Max Activating Token Index: 1022

Text #8

Max Range: 1.4358. Min Range: -1.4358

Max Act: 1.3716. Min Act: -0.0625

Data Index: 5131828 (Open Web Text)

Max Activating Token Index: 1010

Text #9

Max Range: 1.4358. Min Range: -1.4358

Max Act: 1.3758. Min Act: -0.1247

Data Index: 5596280 (Open Web Text)

Max Activating Token Index: 369

Text #10

Max Range: 1.4358. Min Range: -1.4358

Max Act: 1.3672. Min Act: -0.0945

Data Index: 3756596 (Open Web Text)

Max Activating Token Index: 1012

Text #11

Max Range: 1.4358. Min Range: -1.4358

Max Act: 1.3621. Min Act: -0.0570

Data Index: 3860208 (Open Web Text)

Max Activating Token Index: 279

Text #12

Max Range: 1.4358. Min Range: -1.4358

Max Act: 1.3610. Min Act: -0.1182

Data Index: 4544724 (Open Web Text)

Max Activating Token Index: 557

Text #13

Max Range: 1.4358. Min Range: -1.4358

Max Act: 1.3549. Min Act: -0.0942

Data Index: 967082 (Open Web Text)

Max Activating Token Index: 1015

Text #14

Max Range: 1.4358. Min Range: -1.4358

Max Act: 1.3645. Min Act: -0.1338

Data Index: 5965637 (Open Web Text)

Max Activating Token Index: 635

Text #15

Max Range: 1.4358. Min Range: -1.4358

Max Act: 1.3708. Min Act: -0.1006

Data Index: 5705144 (Open Web Text)

Max Activating Token Index: 1011

Text #16

Max Range: 1.4358. Min Range: -1.4358

Max Act: 1.3691. Min Act: -0.1214

Data Index: 8236104 (Open Web Text)

Max Activating Token Index: 262

Text #17

Max Range: 1.4358. Min Range: -1.4358

Max Act: 1.3588. Min Act: -0.0984

Data Index: 7230544 (Open Web Text)

Max Activating Token Index: 574

Text #18

Max Range: 1.4358. Min Range: -1.4358

Max Act: 1.3574. Min Act: -0.1457

Data Index: 4544100 (Open Web Text)

Max Activating Token Index: 1011

Text #19

Max Range: 1.4358. Min Range: -1.4358

Max Act: 1.3518. Min Act: 0.0309

Data Index: 6624901 (Open Web Text)

Max Activating Token Index: 242