Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 390 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.3682. Min Range: -0.3682

Max Act: 0.3682. Min Act: -0.0001

Data Index: 647013 (C4 (Web Text))

Max Activating Token Index: 51

Text #1

Max Range: 0.3682. Min Range: -0.3682

Max Act: 0.3421. Min Act: -0.0000

Data Index: 1090165 (C4 (Web Text))

Max Activating Token Index: 607

Text #2

Max Range: 0.3682. Min Range: -0.3682

Max Act: 0.3165. Min Act: -0.0000

Data Index: 49603 (C4 (Web Text))

Max Activating Token Index: 951

Text #3

Max Range: 0.3682. Min Range: -0.3682

Max Act: 0.2924. Min Act: -0.0000

Data Index: 1346540 (C4 (Web Text))

Max Activating Token Index: 728

Text #4

Max Range: 0.3682. Min Range: -0.3682

Max Act: 0.3259. Min Act: -0.0000

Data Index: 91930 (C4 (Web Text))

Max Activating Token Index: 86

Text #5

Max Range: 0.3682. Min Range: -0.3682

Max Act: 0.2625. Min Act: -0.0000

Data Index: 219014 (C4 (Web Text))

Max Activating Token Index: 604

Text #6

Max Range: 0.3682. Min Range: -0.3682

Max Act: 0.2649. Min Act: -0.0000

Data Index: 290702 (C4 (Web Text))

Max Activating Token Index: 469

Text #7

Max Range: 0.3682. Min Range: -0.3682

Max Act: 0.2483. Min Act: -0.0000

Data Index: 836263 (C4 (Web Text))

Max Activating Token Index: 157

Text #8

Max Range: 0.3682. Min Range: -0.3682

Max Act: 0.2564. Min Act: -0.0000

Data Index: 750451 (C4 (Web Text))

Max Activating Token Index: 478

Text #9

Max Range: 0.3682. Min Range: -0.3682

Max Act: 0.2452. Min Act: -0.0000

Data Index: 1123579 (C4 (Web Text))

Max Activating Token Index: 98

Text #10

Max Range: 0.3682. Min Range: -0.3682

Max Act: 0.2450. Min Act: -0.0000

Data Index: 669756 (C4 (Web Text))

Max Activating Token Index: 388

Text #11

Max Range: 0.3682. Min Range: -0.3682

Max Act: 0.2263. Min Act: -0.0000

Data Index: 475717 (C4 (Web Text))

Max Activating Token Index: 148

Text #12

Max Range: 0.3682. Min Range: -0.3682

Max Act: 0.2504. Min Act: -0.0000

Data Index: 276379 (C4 (Web Text))

Max Activating Token Index: 586

Text #13

Max Range: 0.3682. Min Range: -0.3682

Max Act: 0.2380. Min Act: -0.0000

Data Index: 108853 (C4 (Web Text))

Max Activating Token Index: 168

Text #14

Max Range: 0.3682. Min Range: -0.3682

Max Act: 0.2338. Min Act: -0.0000

Data Index: 261351 (C4 (Web Text))

Max Activating Token Index: 820

Text #15

Max Range: 0.3682. Min Range: -0.3682

Max Act: 0.2275. Min Act: -0.0000

Data Index: 196700 (C4 (Web Text))

Max Activating Token Index: 190

Text #16

Max Range: 0.3682. Min Range: -0.3682

Max Act: 0.2215. Min Act: -0.0000

Data Index: 1177984 (C4 (Web Text))

Max Activating Token Index: 78

Text #17

Max Range: 0.3682. Min Range: -0.3682

Max Act: 0.2443. Min Act: -0.0000

Data Index: 521548 (C4 (Web Text))

Max Activating Token Index: 899

Text #18

Max Range: 0.3682. Min Range: -0.3682

Max Act: 0.2342. Min Act: -0.0000

Data Index: 1346994 (C4 (Web Text))

Max Activating Token Index: 332

Text #19

Max Range: 0.3682. Min Range: -0.3682

Max Act: 0.2330. Min Act: -0.0000

Data Index: 779727 (C4 (Web Text))

Max Activating Token Index: 475