Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 577 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.2316. Min Range: -2.2316

Max Act: 2.0538. Min Act: -0.0000

Data Index: 1242589 (C4 (Web Text))

Max Activating Token Index: 485

Text #1

Max Range: 2.2316. Min Range: -2.2316

Max Act: 2.2316. Min Act: -0.0000

Data Index: 387539 (C4 (Web Text))

Max Activating Token Index: 928

Text #2

Max Range: 2.2316. Min Range: -2.2316

Max Act: 1.9299. Min Act: -0.0000

Data Index: 697315 (C4 (Web Text))

Max Activating Token Index: 89

Text #3

Max Range: 2.2316. Min Range: -2.2316

Max Act: 1.8723. Min Act: -0.0000

Data Index: 289614 (C4 (Web Text))

Max Activating Token Index: 856

Text #4

Max Range: 2.2316. Min Range: -2.2316

Max Act: 1.7470. Min Act: -0.0000

Data Index: 614503 (C4 (Web Text))

Max Activating Token Index: 763

Text #5

Max Range: 2.2316. Min Range: -2.2316

Max Act: 1.8061. Min Act: -0.0000

Data Index: 16023 (C4 (Web Text))

Max Activating Token Index: 365

Text #6

Max Range: 2.2316. Min Range: -2.2316

Max Act: 1.6521. Min Act: -0.0000

Data Index: 1245560 (C4 (Web Text))

Max Activating Token Index: 836

Text #7

Max Range: 2.2316. Min Range: -2.2316

Max Act: 1.7803. Min Act: -0.0000

Data Index: 607442 (C4 (Web Text))

Max Activating Token Index: 57

Text #8

Max Range: 2.2316. Min Range: -2.2316

Max Act: 1.6522. Min Act: -0.0000

Data Index: 2994 (C4 (Web Text))

Max Activating Token Index: 412

Text #9

Max Range: 2.2316. Min Range: -2.2316

Max Act: 1.6192. Min Act: -0.0000

Data Index: 61339 (C4 (Web Text))

Max Activating Token Index: 602

Text #10

Max Range: 2.2316. Min Range: -2.2316

Max Act: 1.5274. Min Act: -0.0000

Data Index: 1005874 (C4 (Web Text))

Max Activating Token Index: 437

Text #11

Max Range: 2.2316. Min Range: -2.2316

Max Act: 1.4684. Min Act: -0.0000

Data Index: 1009480 (C4 (Web Text))

Max Activating Token Index: 363

Text #12

Max Range: 2.2316. Min Range: -2.2316

Max Act: 1.4747. Min Act: -0.0000

Data Index: 858492 (C4 (Web Text))

Max Activating Token Index: 503

Text #13

Max Range: 2.2316. Min Range: -2.2316

Max Act: 1.4508. Min Act: -0.0000

Data Index: 426235 (C4 (Web Text))

Max Activating Token Index: 76

Text #14

Max Range: 2.2316. Min Range: -2.2316

Max Act: 1.4341. Min Act: -0.0000

Data Index: 592456 (C4 (Web Text))

Max Activating Token Index: 148

Text #15

Max Range: 2.2316. Min Range: -2.2316

Max Act: 1.5755. Min Act: -0.0000

Data Index: 93751 (C4 (Web Text))

Max Activating Token Index: 607

Text #16

Max Range: 2.2316. Min Range: -2.2316

Max Act: 1.2136. Min Act: -0.0000

Data Index: 1277669 (C4 (Web Text))

Max Activating Token Index: 87

Text #17

Max Range: 2.2316. Min Range: -2.2316

Max Act: 1.1975. Min Act: -0.0000

Data Index: 289275 (C4 (Web Text))

Max Activating Token Index: 702

Text #18

Max Range: 2.2316. Min Range: -2.2316

Max Act: 1.1444. Min Act: -0.0000

Data Index: 376899 (C4 (Web Text))

Max Activating Token Index: 226

Text #19

Max Range: 2.2316. Min Range: -2.2316

Max Act: 1.1414. Min Act: -0.0000

Data Index: 1233892 (C4 (Web Text))

Max Activating Token Index: 316