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

Dataset: The Pile

Neuron 3328 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5428. Min Range: -1.5428

Max Act: 1.5428. Min Act: -0.0000

Data Index: 1632307 (The Pile)

Max Activating Token Index: 622

Text #1

Max Range: 1.5428. Min Range: -1.5428

Max Act: 1.4898. Min Act: -0.0000

Data Index: 1664387 (The Pile)

Max Activating Token Index: 957

Text #2

Max Range: 1.5428. Min Range: -1.5428

Max Act: 1.4489. Min Act: -0.0000

Data Index: 256254 (The Pile)

Max Activating Token Index: 437

Text #3

Max Range: 1.5428. Min Range: -1.5428

Max Act: 1.3999. Min Act: -0.0000

Data Index: 817853 (The Pile)

Max Activating Token Index: 246

Text #4

Max Range: 1.5428. Min Range: -1.5428

Max Act: 1.4367. Min Act: -0.0000

Data Index: 122599 (The Pile)

Max Activating Token Index: 866

Text #5

Max Range: 1.5428. Min Range: -1.5428

Max Act: 1.2747. Min Act: -0.0000

Data Index: 1368780 (The Pile)

Max Activating Token Index: 195

Text #6

Max Range: 1.5428. Min Range: -1.5428

Max Act: 1.3030. Min Act: -0.0000

Data Index: 905145 (The Pile)

Max Activating Token Index: 592

Text #7

Max Range: 1.5428. Min Range: -1.5428

Max Act: 1.2333. Min Act: 0.0000

Data Index: 718718 (The Pile)

Max Activating Token Index: 939

Text #8

Max Range: 1.5428. Min Range: -1.5428

Max Act: 1.1517. Min Act: -0.0000

Data Index: 1364766 (The Pile)

Max Activating Token Index: 1009

Text #9

Max Range: 1.5428. Min Range: -1.5428

Max Act: 1.1512. Min Act: -0.0000

Data Index: 1360779 (The Pile)

Max Activating Token Index: 757

Text #10

Max Range: 1.5428. Min Range: -1.5428

Max Act: 1.1799. Min Act: -0.0000

Data Index: 1168842 (The Pile)

Max Activating Token Index: 43

Text #11

Max Range: 1.5428. Min Range: -1.5428

Max Act: 1.1811. Min Act: 0.0000

Data Index: 1347512 (The Pile)

Max Activating Token Index: 817

Text #12

Max Range: 1.5428. Min Range: -1.5428

Max Act: 1.1653. Min Act: -0.0000

Data Index: 1104925 (The Pile)

Max Activating Token Index: 62

Text #13

Max Range: 1.5428. Min Range: -1.5428

Max Act: 1.0195. Min Act: -0.0000

Data Index: 156263 (The Pile)

Max Activating Token Index: 939

Text #14

Max Range: 1.5428. Min Range: -1.5428

Max Act: 1.0302. Min Act: -0.0000

Data Index: 615267 (The Pile)

Max Activating Token Index: 601

Text #15

Max Range: 1.5428. Min Range: -1.5428

Max Act: 1.1876. Min Act: -0.0000

Data Index: 302606 (The Pile)

Max Activating Token Index: 573

Text #16

Max Range: 1.5428. Min Range: -1.5428

Max Act: 1.0749. Min Act: -0.0000

Data Index: 199500 (The Pile)

Max Activating Token Index: 52

Text #17

Max Range: 1.5428. Min Range: -1.5428

Max Act: 1.1139. Min Act: -0.0000

Data Index: 1031802 (The Pile)

Max Activating Token Index: 697

Text #18

Max Range: 1.5428. Min Range: -1.5428

Max Act: 1.0543. Min Act: -0.0000

Data Index: 126101 (The Pile)

Max Activating Token Index: 144

Text #19

Max Range: 1.5428. Min Range: -1.5428

Max Act: 1.0359. Min Act: -0.0000

Data Index: 33674 (The Pile)

Max Activating Token Index: 271