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

Dataset: The Pile

Neuron 4306 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: 0.5907. Min Range: -0.5907

Max Act: 0.5907. Min Act: -0.0000

Data Index: 1754720 (The Pile)

Max Activating Token Index: 995

Text #1

Max Range: 0.5907. Min Range: -0.5907

Max Act: 0.3362. Min Act: -0.0000

Data Index: 604779 (The Pile)

Max Activating Token Index: 430

Text #2

Max Range: 0.5907. Min Range: -0.5907

Max Act: 0.3344. Min Act: -0.0000

Data Index: 366975 (The Pile)

Max Activating Token Index: 698

Text #3

Max Range: 0.5907. Min Range: -0.5907

Max Act: 0.3322. Min Act: -0.0000

Data Index: 1076692 (The Pile)

Max Activating Token Index: 621

Text #4

Max Range: 0.5907. Min Range: -0.5907

Max Act: 0.3109. Min Act: -0.0000

Data Index: 1795465 (The Pile)

Max Activating Token Index: 969

Text #5

Max Range: 0.5907. Min Range: -0.5907

Max Act: 0.3208. Min Act: -0.0000

Data Index: 222833 (The Pile)

Max Activating Token Index: 417

Text #6

Max Range: 0.5907. Min Range: -0.5907

Max Act: 0.2904. Min Act: -0.0000

Data Index: 1664642 (The Pile)

Max Activating Token Index: 929

Text #7

Max Range: 0.5907. Min Range: -0.5907

Max Act: 0.2608. Min Act: -0.0000

Data Index: 596491 (The Pile)

Max Activating Token Index: 1021

Text #8

Max Range: 0.5907. Min Range: -0.5907

Max Act: 0.2635. Min Act: -0.0000

Data Index: 934214 (The Pile)

Max Activating Token Index: 785

Text #9

Max Range: 0.5907. Min Range: -0.5907

Max Act: 0.2273. Min Act: -0.0000

Data Index: 1879388 (The Pile)

Max Activating Token Index: 692

Text #10

Max Range: 0.5907. Min Range: -0.5907

Max Act: 0.2380. Min Act: -0.0000

Data Index: 66203 (The Pile)

Max Activating Token Index: 154

Text #11

Max Range: 0.5907. Min Range: -0.5907

Max Act: 0.2463. Min Act: -0.0000

Data Index: 1590135 (The Pile)

Max Activating Token Index: 330

Text #12

Max Range: 0.5907. Min Range: -0.5907

Max Act: 0.2599. Min Act: -0.0000

Data Index: 1815835 (The Pile)

Max Activating Token Index: 190

Text #13

Max Range: 0.5907. Min Range: -0.5907

Max Act: 0.2399. Min Act: -0.0000

Data Index: 116085 (The Pile)

Max Activating Token Index: 880

Text #14

Max Range: 0.5907. Min Range: -0.5907

Max Act: 0.2421. Min Act: -0.0000

Data Index: 1675372 (The Pile)

Max Activating Token Index: 548

Text #15

Max Range: 0.5907. Min Range: -0.5907

Max Act: 0.2432. Min Act: -0.0000

Data Index: 1353634 (The Pile)

Max Activating Token Index: 435

Text #16

Max Range: 0.5907. Min Range: -0.5907

Max Act: 0.2508. Min Act: -0.0000

Data Index: 1748384 (The Pile)

Max Activating Token Index: 939

Text #17

Max Range: 0.5907. Min Range: -0.5907

Max Act: 0.2434. Min Act: -0.0000

Data Index: 951621 (The Pile)

Max Activating Token Index: 541

Text #18

Max Range: 0.5907. Min Range: -0.5907

Max Act: 0.2377. Min Act: -0.0000

Data Index: 1714912 (The Pile)

Max Activating Token Index: 400

Text #19

Max Range: 0.5907. Min Range: -0.5907

Max Act: 0.2349. Min Act: -0.0000

Data Index: 1567442 (The Pile)

Max Activating Token Index: 406