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

Dataset: Open Web Text

Neuron 1590 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: 1.5497. Min Range: -1.5497

Max Act: 1.5497. Min Act: -0.1261

Data Index: 4744184 (Open Web Text)

Max Activating Token Index: 639

Text #1

Max Range: 1.5497. Min Range: -1.5497

Max Act: 1.5430. Min Act: -0.0815

Data Index: 1315954 (Open Web Text)

Max Activating Token Index: 11

Text #2

Max Range: 1.5497. Min Range: -1.5497

Max Act: 1.5242. Min Act: -0.1206

Data Index: 4744186 (Open Web Text)

Max Activating Token Index: 1005

Text #3

Max Range: 1.5497. Min Range: -1.5497

Max Act: 1.4955. Min Act: -0.1684

Data Index: 3008946 (Open Web Text)

Max Activating Token Index: 423

Text #4

Max Range: 1.5497. Min Range: -1.5497

Max Act: 1.4797. Min Act: -0.1699

Data Index: 3364266 (Open Web Text)

Max Activating Token Index: 404

Text #5

Max Range: 1.5497. Min Range: -1.5497

Max Act: 1.4810. Min Act: -0.1667

Data Index: 6417290 (Open Web Text)

Max Activating Token Index: 325

Text #6

Max Range: 1.5497. Min Range: -1.5497

Max Act: 1.4675. Min Act: -0.1700

Data Index: 7999533 (Open Web Text)

Max Activating Token Index: 523

Text #7

Max Range: 1.5497. Min Range: -1.5497

Max Act: 1.4673. Min Act: -0.1699

Data Index: 6417288 (Open Web Text)

Max Activating Token Index: 1017

Text #8

Max Range: 1.5497. Min Range: -1.5497

Max Act: 1.4607. Min Act: -0.1511

Data Index: 6135782 (Open Web Text)

Max Activating Token Index: 907

Text #9

Max Range: 1.5497. Min Range: -1.5497

Max Act: 1.4597. Min Act: -0.1700

Data Index: 2783446 (Open Web Text)

Max Activating Token Index: 428

Text #10

Max Range: 1.5497. Min Range: -1.5497

Max Act: 1.4637. Min Act: -0.1665

Data Index: 6942458 (Open Web Text)

Max Activating Token Index: 165

Text #11

Max Range: 1.5497. Min Range: -1.5497

Max Act: 1.4514. Min Act: -0.1563

Data Index: 6135792 (Open Web Text)

Max Activating Token Index: 895

Text #12

Max Range: 1.5497. Min Range: -1.5497

Max Act: 1.4561. Min Act: -0.1677

Data Index: 4744183 (Open Web Text)

Max Activating Token Index: 1017

Text #13

Max Range: 1.5497. Min Range: -1.5497

Max Act: 1.4515. Min Act: -0.1594

Data Index: 6135788 (Open Web Text)

Max Activating Token Index: 160

Text #14

Max Range: 1.5497. Min Range: -1.5497

Max Act: 1.4527. Min Act: -0.1700

Data Index: 5260551 (Open Web Text)

Max Activating Token Index: 555

Text #15

Max Range: 1.5497. Min Range: -1.5497

Max Act: 1.4437. Min Act: -0.1502

Data Index: 6135793 (Open Web Text)

Max Activating Token Index: 435

Text #16

Max Range: 1.5497. Min Range: -1.5497

Max Act: 1.4454. Min Act: -0.1662

Data Index: 627178 (Open Web Text)

Max Activating Token Index: 210

Text #17

Max Range: 1.5497. Min Range: -1.5497

Max Act: 1.4447. Min Act: -0.1695

Data Index: 4951609 (Open Web Text)

Max Activating Token Index: 620

Text #18

Max Range: 1.5497. Min Range: -1.5497

Max Act: 1.4456. Min Act: -0.1695

Data Index: 6942461 (Open Web Text)

Max Activating Token Index: 538

Text #19

Max Range: 1.5497. Min Range: -1.5497

Max Act: 1.4427. Min Act: -0.1598

Data Index: 7406717 (Open Web Text)

Max Activating Token Index: 250