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

Dataset: The Pile

Neuron 2246 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3038. Min Range: -0.3038

Max Act: 0.2964. Min Act: -0.0000

Data Index: 1229500 (The Pile)

Max Activating Token Index: 447

Text #1

Max Range: 0.3038. Min Range: -0.3038

Max Act: 0.3038. Min Act: -0.0000

Data Index: 1133704 (The Pile)

Max Activating Token Index: 216

Text #2

Max Range: 0.3038. Min Range: -0.3038

Max Act: 0.2993. Min Act: -0.0000

Data Index: 1228108 (The Pile)

Max Activating Token Index: 921

Text #3

Max Range: 0.3038. Min Range: -0.3038

Max Act: 0.2928. Min Act: -0.0000

Data Index: 762132 (The Pile)

Max Activating Token Index: 564

Text #4

Max Range: 0.3038. Min Range: -0.3038

Max Act: 0.2531. Min Act: -0.0000

Data Index: 1663982 (The Pile)

Max Activating Token Index: 488

Text #5

Max Range: 0.3038. Min Range: -0.3038

Max Act: 0.2552. Min Act: -0.0000

Data Index: 648978 (The Pile)

Max Activating Token Index: 1010

Text #6

Max Range: 0.3038. Min Range: -0.3038

Max Act: 0.2662. Min Act: -0.0000

Data Index: 1694607 (The Pile)

Max Activating Token Index: 330

Text #7

Max Range: 0.3038. Min Range: -0.3038

Max Act: 0.2706. Min Act: -0.0000

Data Index: 398697 (The Pile)

Max Activating Token Index: 611

Text #8

Max Range: 0.3038. Min Range: -0.3038

Max Act: 0.2229. Min Act: -0.0000

Data Index: 933384 (The Pile)

Max Activating Token Index: 689

Text #9

Max Range: 0.3038. Min Range: -0.3038

Max Act: 0.2602. Min Act: -0.0000

Data Index: 1220099 (The Pile)

Max Activating Token Index: 797

Text #10

Max Range: 0.3038. Min Range: -0.3038

Max Act: 0.2586. Min Act: -0.0000

Data Index: 1424191 (The Pile)

Max Activating Token Index: 512

Text #11

Max Range: 0.3038. Min Range: -0.3038

Max Act: 0.2660. Min Act: -0.0000

Data Index: 283633 (The Pile)

Max Activating Token Index: 90

Text #12

Max Range: 0.3038. Min Range: -0.3038

Max Act: 0.2576. Min Act: -0.0000

Data Index: 1083630 (The Pile)

Max Activating Token Index: 599

Text #13

Max Range: 0.3038. Min Range: -0.3038

Max Act: 0.2629. Min Act: -0.0000

Data Index: 458585 (The Pile)

Max Activating Token Index: 516

Text #14

Max Range: 0.3038. Min Range: -0.3038

Max Act: 0.2491. Min Act: -0.0000

Data Index: 1732866 (The Pile)

Max Activating Token Index: 946

Text #15

Max Range: 0.3038. Min Range: -0.3038

Max Act: 0.2300. Min Act: -0.0000

Data Index: 1167088 (The Pile)

Max Activating Token Index: 682

Text #16

Max Range: 0.3038. Min Range: -0.3038

Max Act: 0.2271. Min Act: -0.0000

Data Index: 290332 (The Pile)

Max Activating Token Index: 383

Text #17

Max Range: 0.3038. Min Range: -0.3038

Max Act: 0.2248. Min Act: -0.0000

Data Index: 1031291 (The Pile)

Max Activating Token Index: 778

Text #18

Max Range: 0.3038. Min Range: -0.3038

Max Act: 0.2337. Min Act: -0.0000

Data Index: 1148028 (The Pile)

Max Activating Token Index: 475

Text #19

Max Range: 0.3038. Min Range: -0.3038

Max Act: 0.2230. Min Act: -0.0000

Data Index: 396393 (The Pile)

Max Activating Token Index: 999