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

Dataset: Open Web Text

Neuron 4 in Layer 3

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: 5.1469. Min Range: -5.1469

Max Act: 5.1469. Min Act: -0.1700

Data Index: 1911961 (Open Web Text)

Max Activating Token Index: 402

Text #1

Max Range: 5.1469. Min Range: -5.1469

Max Act: 4.8760. Min Act: -0.1700

Data Index: 2733162 (Open Web Text)

Max Activating Token Index: 506

Text #2

Max Range: 5.1469. Min Range: -5.1469

Max Act: 4.8655. Min Act: -0.1700

Data Index: 4366594 (Open Web Text)

Max Activating Token Index: 351

Text #3

Max Range: 5.1469. Min Range: -5.1469

Max Act: 4.9009. Min Act: -0.1700

Data Index: 415575 (Open Web Text)

Max Activating Token Index: 364

Text #4

Max Range: 5.1469. Min Range: -5.1469

Max Act: 4.8383. Min Act: -0.1700

Data Index: 6131347 (Open Web Text)

Max Activating Token Index: 1022

Text #5

Max Range: 5.1469. Min Range: -5.1469

Max Act: 4.8572. Min Act: -0.1700

Data Index: 8333546 (Open Web Text)

Max Activating Token Index: 14

Text #6

Max Range: 5.1469. Min Range: -5.1469

Max Act: 4.8610. Min Act: -0.1700

Data Index: 7870998 (Open Web Text)

Max Activating Token Index: 917

Text #7

Max Range: 5.1469. Min Range: -5.1469

Max Act: 4.8427. Min Act: -0.1700

Data Index: 7406290 (Open Web Text)

Max Activating Token Index: 13

Text #8

Max Range: 5.1469. Min Range: -5.1469

Max Act: 4.8531. Min Act: -0.1700

Data Index: 3063285 (Open Web Text)

Max Activating Token Index: 852

Text #9

Max Range: 5.1469. Min Range: -5.1469

Max Act: 4.8315. Min Act: -0.1700

Data Index: 4269632 (Open Web Text)

Max Activating Token Index: 60

Text #10

Max Range: 5.1469. Min Range: -5.1469

Max Act: 4.8554. Min Act: -0.1700

Data Index: 2038534 (Open Web Text)

Max Activating Token Index: 105

Text #11

Max Range: 5.1469. Min Range: -5.1469

Max Act: 4.8364. Min Act: -0.1700

Data Index: 4517405 (Open Web Text)

Max Activating Token Index: 100

Text #12

Max Range: 5.1469. Min Range: -5.1469

Max Act: 4.8040. Min Act: -0.1700

Data Index: 1116982 (Open Web Text)

Max Activating Token Index: 916

Text #13

Max Range: 5.1469. Min Range: -5.1469

Max Act: 4.7739. Min Act: -0.1700

Data Index: 5414788 (Open Web Text)

Max Activating Token Index: 456

Text #14

Max Range: 5.1469. Min Range: -5.1469

Max Act: 4.7465. Min Act: -0.1700

Data Index: 1455060 (Open Web Text)

Max Activating Token Index: 981

Text #15

Max Range: 5.1469. Min Range: -5.1469

Max Act: 4.8586. Min Act: -0.1700

Data Index: 5955199 (Open Web Text)

Max Activating Token Index: 735

Text #16

Max Range: 5.1469. Min Range: -5.1469

Max Act: 4.8058. Min Act: -0.1700

Data Index: 5651776 (Open Web Text)

Max Activating Token Index: 6

Text #17

Max Range: 5.1469. Min Range: -5.1469

Max Act: 4.7897. Min Act: -0.1700

Data Index: 5689788 (Open Web Text)

Max Activating Token Index: 48

Text #18

Max Range: 5.1469. Min Range: -5.1469

Max Act: 4.8468. Min Act: -0.1700

Data Index: 1744304 (Open Web Text)

Max Activating Token Index: 19

Text #19

Max Range: 5.1469. Min Range: -5.1469

Max Act: 4.7927. Min Act: -0.1700

Data Index: 1326000 (Open Web Text)

Max Activating Token Index: 1011