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

Dataset: The Pile

Neuron 3145 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: 0.4349. Min Range: -0.4349

Max Act: 0.4349. Min Act: -0.0000

Data Index: 218598 (The Pile)

Max Activating Token Index: 542

Text #1

Max Range: 0.4349. Min Range: -0.4349

Max Act: 0.3795. Min Act: -0.0000

Data Index: 1955035 (The Pile)

Max Activating Token Index: 696

Text #2

Max Range: 0.4349. Min Range: -0.4349

Max Act: 0.2968. Min Act: -0.0000

Data Index: 185682 (The Pile)

Max Activating Token Index: 845

Text #3

Max Range: 0.4349. Min Range: -0.4349

Max Act: 0.3214. Min Act: -0.0000

Data Index: 328451 (The Pile)

Max Activating Token Index: 962

Text #4

Max Range: 0.4349. Min Range: -0.4349

Max Act: 0.2959. Min Act: -0.0000

Data Index: 1734198 (The Pile)

Max Activating Token Index: 254

Text #5

Max Range: 0.4349. Min Range: -0.4349

Max Act: 0.2825. Min Act: -0.0000

Data Index: 740673 (The Pile)

Max Activating Token Index: 680

Text #6

Max Range: 0.4349. Min Range: -0.4349

Max Act: 0.2882. Min Act: -0.0000

Data Index: 1256236 (The Pile)

Max Activating Token Index: 923

Text #7

Max Range: 0.4349. Min Range: -0.4349

Max Act: 0.2845. Min Act: -0.0000

Data Index: 1752525 (The Pile)

Max Activating Token Index: 299

Text #8

Max Range: 0.4349. Min Range: -0.4349

Max Act: 0.2623. Min Act: -0.0000

Data Index: 969901 (The Pile)

Max Activating Token Index: 931

Text #9

Max Range: 0.4349. Min Range: -0.4349

Max Act: 0.2531. Min Act: -0.0000

Data Index: 302843 (The Pile)

Max Activating Token Index: 558

Text #10

Max Range: 0.4349. Min Range: -0.4349

Max Act: 0.2358. Min Act: -0.0000

Data Index: 1171746 (The Pile)

Max Activating Token Index: 825

Text #11

Max Range: 0.4349. Min Range: -0.4349

Max Act: 0.2422. Min Act: -0.0000

Data Index: 697860 (The Pile)

Max Activating Token Index: 815

Text #12

Max Range: 0.4349. Min Range: -0.4349

Max Act: 0.2383. Min Act: -0.0000

Data Index: 715749 (The Pile)

Max Activating Token Index: 972

Text #13

Max Range: 0.4349. Min Range: -0.4349

Max Act: 0.2470. Min Act: -0.0000

Data Index: 8686 (The Pile)

Max Activating Token Index: 380

Text #14

Max Range: 0.4349. Min Range: -0.4349

Max Act: 0.2398. Min Act: -0.0000

Data Index: 195390 (The Pile)

Max Activating Token Index: 453

Text #15

Max Range: 0.4349. Min Range: -0.4349

Max Act: 0.2421. Min Act: -0.0000

Data Index: 623693 (The Pile)

Max Activating Token Index: 778

Text #16

Max Range: 0.4349. Min Range: -0.4349

Max Act: 0.2205. Min Act: -0.0000

Data Index: 1184972 (The Pile)

Max Activating Token Index: 943

Text #17

Max Range: 0.4349. Min Range: -0.4349

Max Act: 0.2169. Min Act: -0.0000

Data Index: 1733719 (The Pile)

Max Activating Token Index: 579

Text #18

Max Range: 0.4349. Min Range: -0.4349

Max Act: 0.2066. Min Act: -0.0000

Data Index: 1827276 (The Pile)

Max Activating Token Index: 370

Text #19

Max Range: 0.4349. Min Range: -0.4349

Max Act: 0.2327. Min Act: -0.0000

Data Index: 1262597 (The Pile)

Max Activating Token Index: 714