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

Dataset: Open Web Text

Neuron 2616 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: 1.5275. Min Range: -1.5275

Max Act: 1.5275. Min Act: -0.1700

Data Index: 1622481 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 1.5275. Min Range: -1.5275

Max Act: 1.4620. Min Act: -0.1699

Data Index: 3738824 (Open Web Text)

Max Activating Token Index: 3

Text #2

Max Range: 1.5275. Min Range: -1.5275

Max Act: 1.4651. Min Act: -0.1699

Data Index: 1742966 (Open Web Text)

Max Activating Token Index: 3

Text #3

Max Range: 1.5275. Min Range: -1.5275

Max Act: 1.4620. Min Act: -0.1700

Data Index: 8122261 (Open Web Text)

Max Activating Token Index: 3

Text #4

Max Range: 1.5275. Min Range: -1.5275

Max Act: 1.4608. Min Act: -0.1674

Data Index: 5141692 (Open Web Text)

Max Activating Token Index: 4

Text #5

Max Range: 1.5275. Min Range: -1.5275

Max Act: 1.4503. Min Act: -0.1700

Data Index: 5965627 (Open Web Text)

Max Activating Token Index: 3

Text #6

Max Range: 1.5275. Min Range: -1.5275

Max Act: 1.4538. Min Act: -0.1697

Data Index: 8313385 (Open Web Text)

Max Activating Token Index: 232

Text #7

Max Range: 1.5275. Min Range: -1.5275

Max Act: 1.4521. Min Act: -0.1699

Data Index: 8153870 (Open Web Text)

Max Activating Token Index: 15

Text #8

Max Range: 1.5275. Min Range: -1.5275

Max Act: 1.4456. Min Act: -0.1700

Data Index: 7712888 (Open Web Text)

Max Activating Token Index: 17

Text #9

Max Range: 1.5275. Min Range: -1.5275

Max Act: 1.4499. Min Act: -0.1700

Data Index: 7457864 (Open Web Text)

Max Activating Token Index: 379

Text #10

Max Range: 1.5275. Min Range: -1.5275

Max Act: 1.4328. Min Act: -0.1700

Data Index: 3906295 (Open Web Text)

Max Activating Token Index: 35

Text #11

Max Range: 1.5275. Min Range: -1.5275

Max Act: 1.4339. Min Act: -0.1696

Data Index: 8566560 (Open Web Text)

Max Activating Token Index: 437

Text #12

Max Range: 1.5275. Min Range: -1.5275

Max Act: 1.4357. Min Act: -0.1700

Data Index: 1471185 (Open Web Text)

Max Activating Token Index: 5

Text #13

Max Range: 1.5275. Min Range: -1.5275

Max Act: 1.4351. Min Act: -0.1700

Data Index: 3582428 (Open Web Text)

Max Activating Token Index: 13

Text #14

Max Range: 1.5275. Min Range: -1.5275

Max Act: 1.4254. Min Act: -0.1700

Data Index: 3134173 (Open Web Text)

Max Activating Token Index: 10

Text #15

Max Range: 1.5275. Min Range: -1.5275

Max Act: 1.4233. Min Act: -0.1700

Data Index: 6189153 (Open Web Text)

Max Activating Token Index: 3

Text #16

Max Range: 1.5275. Min Range: -1.5275

Max Act: 1.4186. Min Act: -0.1700

Data Index: 169286 (Open Web Text)

Max Activating Token Index: 35

Text #17

Max Range: 1.5275. Min Range: -1.5275

Max Act: 1.4202. Min Act: -0.1700

Data Index: 1840907 (Open Web Text)

Max Activating Token Index: 14

Text #18

Max Range: 1.5275. Min Range: -1.5275

Max Act: 1.4170. Min Act: -0.1691

Data Index: 7552515 (Open Web Text)

Max Activating Token Index: 71

Text #19

Max Range: 1.5275. Min Range: -1.5275

Max Act: 1.4128. Min Act: -0.1699

Data Index: 3869017 (Open Web Text)

Max Activating Token Index: 6