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

Dataset: Open Web Text

Neuron 1555 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: 1.5442. Min Range: -1.5442

Max Act: 1.5424. Min Act: -0.1691

Data Index: 4947694 (Open Web Text)

Max Activating Token Index: 100

Text #1

Max Range: 1.5442. Min Range: -1.5442

Max Act: 1.5317. Min Act: -0.1637

Data Index: 882413 (Open Web Text)

Max Activating Token Index: 73

Text #2

Max Range: 1.5442. Min Range: -1.5442

Max Act: 1.5442. Min Act: -0.1096

Data Index: 5210364 (Open Web Text)

Max Activating Token Index: 888

Text #3

Max Range: 1.5442. Min Range: -1.5442

Max Act: 1.5320. Min Act: -0.1624

Data Index: 7565001 (Open Web Text)

Max Activating Token Index: 66

Text #4

Max Range: 1.5442. Min Range: -1.5442

Max Act: 1.5282. Min Act: -0.1677

Data Index: 6843984 (Open Web Text)

Max Activating Token Index: 329

Text #5

Max Range: 1.5442. Min Range: -1.5442

Max Act: 1.5173. Min Act: -0.1700

Data Index: 5221566 (Open Web Text)

Max Activating Token Index: 475

Text #6

Max Range: 1.5442. Min Range: -1.5442

Max Act: 1.5112. Min Act: -0.1599

Data Index: 4698414 (Open Web Text)

Max Activating Token Index: 300

Text #7

Max Range: 1.5442. Min Range: -1.5442

Max Act: 1.4992. Min Act: -0.1605

Data Index: 3932816 (Open Web Text)

Max Activating Token Index: 507

Text #8

Max Range: 1.5442. Min Range: -1.5442

Max Act: 1.4930. Min Act: -0.1678

Data Index: 135345 (Open Web Text)

Max Activating Token Index: 789

Text #9

Max Range: 1.5442. Min Range: -1.5442

Max Act: 1.4923. Min Act: -0.1682

Data Index: 2793305 (Open Web Text)

Max Activating Token Index: 906

Text #10

Max Range: 1.5442. Min Range: -1.5442

Max Act: 1.4793. Min Act: -0.1688

Data Index: 5399467 (Open Web Text)

Max Activating Token Index: 52

Text #11

Max Range: 1.5442. Min Range: -1.5442

Max Act: 1.4741. Min Act: -0.1578

Data Index: 4362208 (Open Web Text)

Max Activating Token Index: 156

Text #12

Max Range: 1.5442. Min Range: -1.5442

Max Act: 1.4685. Min Act: -0.1635

Data Index: 2033620 (Open Web Text)

Max Activating Token Index: 166

Text #13

Max Range: 1.5442. Min Range: -1.5442

Max Act: 1.4730. Min Act: -0.1508

Data Index: 4878002 (Open Web Text)

Max Activating Token Index: 593

Text #14

Max Range: 1.5442. Min Range: -1.5442

Max Act: 1.4614. Min Act: -0.1363

Data Index: 3716527 (Open Web Text)

Max Activating Token Index: 805

Text #15

Max Range: 1.5442. Min Range: -1.5442

Max Act: 1.4680. Min Act: -0.1693

Data Index: 7791448 (Open Web Text)

Max Activating Token Index: 390

Text #16

Max Range: 1.5442. Min Range: -1.5442

Max Act: 1.4550. Min Act: -0.1700

Data Index: 5401765 (Open Web Text)

Max Activating Token Index: 289

Text #17

Max Range: 1.5442. Min Range: -1.5442

Max Act: 1.4613. Min Act: -0.1699

Data Index: 7803325 (Open Web Text)

Max Activating Token Index: 330

Text #18

Max Range: 1.5442. Min Range: -1.5442

Max Act: 1.4637. Min Act: -0.1700

Data Index: 7676631 (Open Web Text)

Max Activating Token Index: 401

Text #19

Max Range: 1.5442. Min Range: -1.5442

Max Act: 1.4547. Min Act: -0.1251

Data Index: 1333842 (Open Web Text)

Max Activating Token Index: 413