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

Dataset: The Pile

Neuron 2418 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3943. Min Range: -0.3943

Max Act: 0.3943. Min Act: -0.0000

Data Index: 1083978 (The Pile)

Max Activating Token Index: 410

Text #1

Max Range: 0.3943. Min Range: -0.3943

Max Act: 0.3514. Min Act: -0.0000

Data Index: 1733473 (The Pile)

Max Activating Token Index: 940

Text #2

Max Range: 0.3943. Min Range: -0.3943

Max Act: 0.3579. Min Act: -0.0000

Data Index: 1672327 (The Pile)

Max Activating Token Index: 478

Text #3

Max Range: 0.3943. Min Range: -0.3943

Max Act: 0.3003. Min Act: -0.0000

Data Index: 414998 (The Pile)

Max Activating Token Index: 865

Text #4

Max Range: 0.3943. Min Range: -0.3943

Max Act: 0.2961. Min Act: -0.0000

Data Index: 1859457 (The Pile)

Max Activating Token Index: 158

Text #5

Max Range: 0.3943. Min Range: -0.3943

Max Act: 0.2572. Min Act: -0.0000

Data Index: 1834417 (The Pile)

Max Activating Token Index: 591

Text #6

Max Range: 0.3943. Min Range: -0.3943

Max Act: 0.2452. Min Act: -0.0000

Data Index: 624035 (The Pile)

Max Activating Token Index: 615

Text #7

Max Range: 0.3943. Min Range: -0.3943

Max Act: 0.2690. Min Act: -0.0000

Data Index: 602174 (The Pile)

Max Activating Token Index: 571

Text #8

Max Range: 0.3943. Min Range: -0.3943

Max Act: 0.2501. Min Act: -0.0000

Data Index: 1625816 (The Pile)

Max Activating Token Index: 196

Text #9

Max Range: 0.3943. Min Range: -0.3943

Max Act: 0.2590. Min Act: -0.0000

Data Index: 1215795 (The Pile)

Max Activating Token Index: 372

Text #10

Max Range: 0.3943. Min Range: -0.3943

Max Act: 0.2622. Min Act: 0.0000

Data Index: 951150 (The Pile)

Max Activating Token Index: 748

Text #11

Max Range: 0.3943. Min Range: -0.3943

Max Act: 0.2521. Min Act: -0.0000

Data Index: 1093380 (The Pile)

Max Activating Token Index: 777

Text #12

Max Range: 0.3943. Min Range: -0.3943

Max Act: 0.2410. Min Act: -0.0000

Data Index: 25088 (The Pile)

Max Activating Token Index: 307

Text #13

Max Range: 0.3943. Min Range: -0.3943

Max Act: 0.1781. Min Act: -0.0000

Data Index: 971758 (The Pile)

Max Activating Token Index: 1015

Text #14

Max Range: 0.3943. Min Range: -0.3943

Max Act: 0.2352. Min Act: -0.0000

Data Index: 649819 (The Pile)

Max Activating Token Index: 410

Text #15

Max Range: 0.3943. Min Range: -0.3943

Max Act: 0.2297. Min Act: -0.0000

Data Index: 1763597 (The Pile)

Max Activating Token Index: 453

Text #16

Max Range: 0.3943. Min Range: -0.3943

Max Act: 0.2362. Min Act: -0.0000

Data Index: 154516 (The Pile)

Max Activating Token Index: 704

Text #17

Max Range: 0.3943. Min Range: -0.3943

Max Act: 0.2440. Min Act: -0.0000

Data Index: 431680 (The Pile)

Max Activating Token Index: 445

Text #18

Max Range: 0.3943. Min Range: -0.3943

Max Act: 0.2232. Min Act: -0.0000

Data Index: 1187279 (The Pile)

Max Activating Token Index: 982

Text #19

Max Range: 0.3943. Min Range: -0.3943

Max Act: 0.2288. Min Act: -0.0000

Data Index: 430835 (The Pile)

Max Activating Token Index: 211