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

Dataset: Open Web Text

Neuron 248 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: 1.5318. Min Range: -1.5318

Max Act: 1.5318. Min Act: -0.1699

Data Index: 1091344 (Open Web Text)

Max Activating Token Index: 363

Text #1

Max Range: 1.5318. Min Range: -1.5318

Max Act: 1.4933. Min Act: -0.1690

Data Index: 7453330 (Open Web Text)

Max Activating Token Index: 955

Text #2

Max Range: 1.5318. Min Range: -1.5318

Max Act: 1.5042. Min Act: -0.1700

Data Index: 2490217 (Open Web Text)

Max Activating Token Index: 553

Text #3

Max Range: 1.5318. Min Range: -1.5318

Max Act: 1.4793. Min Act: -0.1700

Data Index: 7323777 (Open Web Text)

Max Activating Token Index: 223

Text #4

Max Range: 1.5318. Min Range: -1.5318

Max Act: 1.4841. Min Act: -0.1700

Data Index: 6069076 (Open Web Text)

Max Activating Token Index: 559

Text #5

Max Range: 1.5318. Min Range: -1.5318

Max Act: 1.4729. Min Act: -0.1700

Data Index: 8712898 (Open Web Text)

Max Activating Token Index: 896

Text #6

Max Range: 1.5318. Min Range: -1.5318

Max Act: 1.4844. Min Act: -0.1693

Data Index: 6587939 (Open Web Text)

Max Activating Token Index: 433

Text #7

Max Range: 1.5318. Min Range: -1.5318

Max Act: 1.4821. Min Act: -0.1687

Data Index: 2651547 (Open Web Text)

Max Activating Token Index: 410

Text #8

Max Range: 1.5318. Min Range: -1.5318

Max Act: 1.4781. Min Act: -0.1700

Data Index: 5904540 (Open Web Text)

Max Activating Token Index: 475

Text #9

Max Range: 1.5318. Min Range: -1.5318

Max Act: 1.4706. Min Act: -0.1692

Data Index: 5747841 (Open Web Text)

Max Activating Token Index: 657

Text #10

Max Range: 1.5318. Min Range: -1.5318

Max Act: 1.4720. Min Act: -0.1694

Data Index: 6757511 (Open Web Text)

Max Activating Token Index: 433

Text #11

Max Range: 1.5318. Min Range: -1.5318

Max Act: 1.4735. Min Act: -0.1700

Data Index: 886517 (Open Web Text)

Max Activating Token Index: 960

Text #12

Max Range: 1.5318. Min Range: -1.5318

Max Act: 1.4746. Min Act: -0.1700

Data Index: 5601472 (Open Web Text)

Max Activating Token Index: 874

Text #13

Max Range: 1.5318. Min Range: -1.5318

Max Act: 1.4734. Min Act: -0.1697

Data Index: 3430954 (Open Web Text)

Max Activating Token Index: 1009

Text #14

Max Range: 1.5318. Min Range: -1.5318

Max Act: 1.4678. Min Act: -0.1700

Data Index: 8104654 (Open Web Text)

Max Activating Token Index: 761

Text #15

Max Range: 1.5318. Min Range: -1.5318

Max Act: 1.4704. Min Act: -0.1699

Data Index: 3535593 (Open Web Text)

Max Activating Token Index: 470

Text #16

Max Range: 1.5318. Min Range: -1.5318

Max Act: 1.4606. Min Act: -0.1700

Data Index: 5031424 (Open Web Text)

Max Activating Token Index: 417

Text #17

Max Range: 1.5318. Min Range: -1.5318

Max Act: 1.4635. Min Act: -0.1685

Data Index: 1272791 (Open Web Text)

Max Activating Token Index: 566

Text #18

Max Range: 1.5318. Min Range: -1.5318

Max Act: 1.4520. Min Act: -0.1700

Data Index: 4573507 (Open Web Text)

Max Activating Token Index: 332

Text #19

Max Range: 1.5318. Min Range: -1.5318

Max Act: 1.4515. Min Act: -0.1700

Data Index: 4536377 (Open Web Text)

Max Activating Token Index: 567