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

Dataset: The Pile

Neuron 3653 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3301. Min Range: -0.3301

Max Act: 0.3032. Min Act: -0.0000

Data Index: 1781332 (The Pile)

Max Activating Token Index: 312

Text #1

Max Range: 0.3301. Min Range: -0.3301

Max Act: 0.2900. Min Act: -0.0000

Data Index: 887143 (The Pile)

Max Activating Token Index: 362

Text #2

Max Range: 0.3301. Min Range: -0.3301

Max Act: 0.2853. Min Act: -0.0000

Data Index: 381432 (The Pile)

Max Activating Token Index: 219

Text #3

Max Range: 0.3301. Min Range: -0.3301

Max Act: 0.3301. Min Act: -0.0000

Data Index: 611173 (The Pile)

Max Activating Token Index: 675

Text #4

Max Range: 0.3301. Min Range: -0.3301

Max Act: 0.2762. Min Act: -0.0000

Data Index: 713168 (The Pile)

Max Activating Token Index: 451

Text #5

Max Range: 0.3301. Min Range: -0.3301

Max Act: 0.2721. Min Act: -0.0000

Data Index: 947097 (The Pile)

Max Activating Token Index: 742

Text #6

Max Range: 0.3301. Min Range: -0.3301

Max Act: 0.2744. Min Act: -0.0000

Data Index: 196835 (The Pile)

Max Activating Token Index: 575

Text #7

Max Range: 0.3301. Min Range: -0.3301

Max Act: 0.2685. Min Act: -0.0000

Data Index: 1479723 (The Pile)

Max Activating Token Index: 311

Text #8

Max Range: 0.3301. Min Range: -0.3301

Max Act: 0.2752. Min Act: -0.0000

Data Index: 1874098 (The Pile)

Max Activating Token Index: 310

Text #9

Max Range: 0.3301. Min Range: -0.3301

Max Act: 0.2444. Min Act: -0.0000

Data Index: 900839 (The Pile)

Max Activating Token Index: 720

Text #10

Max Range: 0.3301. Min Range: -0.3301

Max Act: 0.2502. Min Act: -0.0000

Data Index: 1476390 (The Pile)

Max Activating Token Index: 148

Text #11

Max Range: 0.3301. Min Range: -0.3301

Max Act: 0.2510. Min Act: -0.0000

Data Index: 1314412 (The Pile)

Max Activating Token Index: 560

Text #12

Max Range: 0.3301. Min Range: -0.3301

Max Act: 0.2641. Min Act: -0.0000

Data Index: 1210541 (The Pile)

Max Activating Token Index: 758

Text #13

Max Range: 0.3301. Min Range: -0.3301

Max Act: 0.2375. Min Act: -0.0000

Data Index: 1681290 (The Pile)

Max Activating Token Index: 227

Text #14

Max Range: 0.3301. Min Range: -0.3301

Max Act: 0.2375. Min Act: -0.0000

Data Index: 513633 (The Pile)

Max Activating Token Index: 227

Text #15

Max Range: 0.3301. Min Range: -0.3301

Max Act: 0.2334. Min Act: -0.0000

Data Index: 1990842 (The Pile)

Max Activating Token Index: 639

Text #16

Max Range: 0.3301. Min Range: -0.3301

Max Act: 0.2494. Min Act: -0.0000

Data Index: 818535 (The Pile)

Max Activating Token Index: 463

Text #17

Max Range: 0.3301. Min Range: -0.3301

Max Act: 0.2528. Min Act: -0.0000

Data Index: 1821479 (The Pile)

Max Activating Token Index: 315

Text #18

Max Range: 0.3301. Min Range: -0.3301

Max Act: 0.2383. Min Act: -0.0000

Data Index: 354162 (The Pile)

Max Activating Token Index: 124

Text #19

Max Range: 0.3301. Min Range: -0.3301

Max Act: 0.2453. Min Act: -0.0000

Data Index: 1837059 (The Pile)

Max Activating Token Index: 458