Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3077 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2797. Min Range: -0.2797

Max Act: 0.2797. Min Act: -0.0000

Data Index: 418752 (C4 (Web Text))

Max Activating Token Index: 949

Text #1

Max Range: 0.2797. Min Range: -0.2797

Max Act: 0.2733. Min Act: -0.0001

Data Index: 646475 (C4 (Web Text))

Max Activating Token Index: 579

Text #2

Max Range: 0.2797. Min Range: -0.2797

Max Act: 0.2752. Min Act: -0.0000

Data Index: 1323195 (C4 (Web Text))

Max Activating Token Index: 969

Text #3

Max Range: 0.2797. Min Range: -0.2797

Max Act: 0.2571. Min Act: -0.0000

Data Index: 1046381 (C4 (Web Text))

Max Activating Token Index: 889

Text #4

Max Range: 0.2797. Min Range: -0.2797

Max Act: 0.2591. Min Act: -0.0000

Data Index: 546382 (C4 (Web Text))

Max Activating Token Index: 944

Text #5

Max Range: 0.2797. Min Range: -0.2797

Max Act: 0.2427. Min Act: -0.0000

Data Index: 276907 (C4 (Web Text))

Max Activating Token Index: 312

Text #6

Max Range: 0.2797. Min Range: -0.2797

Max Act: 0.2465. Min Act: -0.0000

Data Index: 40534 (C4 (Web Text))

Max Activating Token Index: 355

Text #7

Max Range: 0.2797. Min Range: -0.2797

Max Act: 0.2487. Min Act: -0.0001

Data Index: 463598 (C4 (Web Text))

Max Activating Token Index: 655

Text #8

Max Range: 0.2797. Min Range: -0.2797

Max Act: 0.2451. Min Act: -0.0001

Data Index: 513156 (C4 (Web Text))

Max Activating Token Index: 961

Text #9

Max Range: 0.2797. Min Range: -0.2797

Max Act: 0.2449. Min Act: -0.0000

Data Index: 1182942 (C4 (Web Text))

Max Activating Token Index: 22

Text #10

Max Range: 0.2797. Min Range: -0.2797

Max Act: 0.2322. Min Act: 0.0000

Data Index: 275910 (C4 (Web Text))

Max Activating Token Index: 354

Text #11

Max Range: 0.2797. Min Range: -0.2797

Max Act: 0.2367. Min Act: -0.0000

Data Index: 1139365 (C4 (Web Text))

Max Activating Token Index: 331

Text #12

Max Range: 0.2797. Min Range: -0.2797

Max Act: 0.2381. Min Act: -0.0001

Data Index: 600108 (C4 (Web Text))

Max Activating Token Index: 520

Text #13

Max Range: 0.2797. Min Range: -0.2797

Max Act: 0.2281. Min Act: -0.0000

Data Index: 555169 (C4 (Web Text))

Max Activating Token Index: 647

Text #14

Max Range: 0.2797. Min Range: -0.2797

Max Act: 0.2273. Min Act: -0.0001

Data Index: 761748 (C4 (Web Text))

Max Activating Token Index: 402

Text #15

Max Range: 0.2797. Min Range: -0.2797

Max Act: 0.2283. Min Act: -0.0000

Data Index: 417259 (C4 (Web Text))

Max Activating Token Index: 268

Text #16

Max Range: 0.2797. Min Range: -0.2797

Max Act: 0.2272. Min Act: -0.0001

Data Index: 292479 (C4 (Web Text))

Max Activating Token Index: 152

Text #17

Max Range: 0.2797. Min Range: -0.2797

Max Act: 0.2272. Min Act: -0.0000

Data Index: 288561 (C4 (Web Text))

Max Activating Token Index: 48

Text #18

Max Range: 0.2797. Min Range: -0.2797

Max Act: 0.2194. Min Act: -0.0000

Data Index: 740814 (C4 (Web Text))

Max Activating Token Index: 453

Text #19

Max Range: 0.2797. Min Range: -0.2797

Max Act: 0.2255. Min Act: -0.0000

Data Index: 538877 (C4 (Web Text))

Max Activating Token Index: 121