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

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

Neuron 999 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: 2.4442. Min Range: -2.4442

Max Act: 2.3402. Min Act: -0.0000

Data Index: 67100 (C4 (Web Text))

Max Activating Token Index: 642

Text #1

Max Range: 2.4442. Min Range: -2.4442

Max Act: 2.4442. Min Act: -0.0000

Data Index: 1127523 (C4 (Web Text))

Max Activating Token Index: 567

Text #2

Max Range: 2.4442. Min Range: -2.4442

Max Act: 2.3827. Min Act: -0.0000

Data Index: 292623 (C4 (Web Text))

Max Activating Token Index: 566

Text #3

Max Range: 2.4442. Min Range: -2.4442

Max Act: 2.2350. Min Act: -0.0000

Data Index: 536135 (C4 (Web Text))

Max Activating Token Index: 783

Text #4

Max Range: 2.4442. Min Range: -2.4442

Max Act: 2.3327. Min Act: -0.0000

Data Index: 445907 (C4 (Web Text))

Max Activating Token Index: 346

Text #5

Max Range: 2.4442. Min Range: -2.4442

Max Act: 2.0847. Min Act: -0.0000

Data Index: 673621 (C4 (Web Text))

Max Activating Token Index: 244

Text #6

Max Range: 2.4442. Min Range: -2.4442

Max Act: 2.3205. Min Act: -0.0000

Data Index: 251579 (C4 (Web Text))

Max Activating Token Index: 69

Text #7

Max Range: 2.4442. Min Range: -2.4442

Max Act: 2.1898. Min Act: -0.0000

Data Index: 966215 (C4 (Web Text))

Max Activating Token Index: 40

Text #8

Max Range: 2.4442. Min Range: -2.4442

Max Act: 2.2466. Min Act: -0.0000

Data Index: 2007 (C4 (Web Text))

Max Activating Token Index: 301

Text #9

Max Range: 2.4442. Min Range: -2.4442

Max Act: 2.2203. Min Act: -0.0000

Data Index: 1042168 (C4 (Web Text))

Max Activating Token Index: 283

Text #10

Max Range: 2.4442. Min Range: -2.4442

Max Act: 2.2088. Min Act: -0.0000

Data Index: 449271 (C4 (Web Text))

Max Activating Token Index: 299

Text #11

Max Range: 2.4442. Min Range: -2.4442

Max Act: 1.5676. Min Act: -0.0000

Data Index: 735528 (C4 (Web Text))

Max Activating Token Index: 683

Text #12

Max Range: 2.4442. Min Range: -2.4442

Max Act: 1.5028. Min Act: -0.0000

Data Index: 1011806 (C4 (Web Text))

Max Activating Token Index: 785

Text #13

Max Range: 2.4442. Min Range: -2.4442

Max Act: 1.3564. Min Act: -0.0000

Data Index: 771269 (C4 (Web Text))

Max Activating Token Index: 419

Text #14

Max Range: 2.4442. Min Range: -2.4442

Max Act: 1.1784. Min Act: -0.0000

Data Index: 831250 (C4 (Web Text))

Max Activating Token Index: 862

Text #15

Max Range: 2.4442. Min Range: -2.4442

Max Act: 1.1474. Min Act: -0.0000

Data Index: 799863 (C4 (Web Text))

Max Activating Token Index: 661

Text #16

Max Range: 2.4442. Min Range: -2.4442

Max Act: 1.2174. Min Act: -0.0000

Data Index: 353634 (C4 (Web Text))

Max Activating Token Index: 791

Text #17

Max Range: 2.4442. Min Range: -2.4442

Max Act: 1.0406. Min Act: -0.0000

Data Index: 936760 (C4 (Web Text))

Max Activating Token Index: 738

Text #18

Max Range: 2.4442. Min Range: -2.4442

Max Act: 0.9947. Min Act: -0.0000

Data Index: 421671 (C4 (Web Text))

Max Activating Token Index: 342

Text #19

Max Range: 2.4442. Min Range: -2.4442

Max Act: 0.9159. Min Act: -0.0000

Data Index: 1447633 (Python Code)

Max Activating Token Index: 895