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

Dataset: The Pile

Neuron 165 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: 1.2796. Min Range: -1.2796

Max Act: 1.2796. Min Act: -0.0000

Data Index: 1157587 (The Pile)

Max Activating Token Index: 148

Text #1

Max Range: 1.2796. Min Range: -1.2796

Max Act: 1.0416. Min Act: -0.0000

Data Index: 1598566 (The Pile)

Max Activating Token Index: 112

Text #2

Max Range: 1.2796. Min Range: -1.2796

Max Act: 1.0594. Min Act: -0.0000

Data Index: 423919 (The Pile)

Max Activating Token Index: 340

Text #3

Max Range: 1.2796. Min Range: -1.2796

Max Act: 0.9651. Min Act: -0.0000

Data Index: 95704 (The Pile)

Max Activating Token Index: 312

Text #4

Max Range: 1.2796. Min Range: -1.2796

Max Act: 0.9655. Min Act: -0.0000

Data Index: 331820 (The Pile)

Max Activating Token Index: 786

Text #5

Max Range: 1.2796. Min Range: -1.2796

Max Act: 0.9300. Min Act: -0.0000

Data Index: 1328335 (The Pile)

Max Activating Token Index: 460

Text #6

Max Range: 1.2796. Min Range: -1.2796

Max Act: 1.0345. Min Act: -0.0000

Data Index: 1796744 (The Pile)

Max Activating Token Index: 903

Text #7

Max Range: 1.2796. Min Range: -1.2796

Max Act: 0.9205. Min Act: -0.0000

Data Index: 1219349 (The Pile)

Max Activating Token Index: 32

Text #8

Max Range: 1.2796. Min Range: -1.2796

Max Act: 0.8831. Min Act: -0.0000

Data Index: 376973 (The Pile)

Max Activating Token Index: 31

Text #9

Max Range: 1.2796. Min Range: -1.2796

Max Act: 0.9434. Min Act: -0.0000

Data Index: 1430631 (The Pile)

Max Activating Token Index: 994

Text #10

Max Range: 1.2796. Min Range: -1.2796

Max Act: 0.8557. Min Act: -0.0000

Data Index: 431692 (The Pile)

Max Activating Token Index: 199

Text #11

Max Range: 1.2796. Min Range: -1.2796

Max Act: 0.8752. Min Act: -0.0000

Data Index: 1186454 (The Pile)

Max Activating Token Index: 113

Text #12

Max Range: 1.2796. Min Range: -1.2796

Max Act: 0.8568. Min Act: -0.0000

Data Index: 1834355 (The Pile)

Max Activating Token Index: 763

Text #13

Max Range: 1.2796. Min Range: -1.2796

Max Act: 0.8462. Min Act: -0.0000

Data Index: 244918 (The Pile)

Max Activating Token Index: 128

Text #14

Max Range: 1.2796. Min Range: -1.2796

Max Act: 0.8707. Min Act: -0.0000

Data Index: 1126061 (The Pile)

Max Activating Token Index: 175

Text #15

Max Range: 1.2796. Min Range: -1.2796

Max Act: 0.8564. Min Act: -0.0000

Data Index: 856606 (The Pile)

Max Activating Token Index: 916

Text #16

Max Range: 1.2796. Min Range: -1.2796

Max Act: 0.8570. Min Act: -0.0000

Data Index: 913170 (The Pile)

Max Activating Token Index: 530

Text #17

Max Range: 1.2796. Min Range: -1.2796

Max Act: 0.8526. Min Act: -0.0000

Data Index: 882263 (The Pile)

Max Activating Token Index: 220

Text #18

Max Range: 1.2796. Min Range: -1.2796

Max Act: 0.8279. Min Act: -0.0000

Data Index: 168626 (The Pile)

Max Activating Token Index: 964

Text #19

Max Range: 1.2796. Min Range: -1.2796

Max Act: 0.7968. Min Act: -0.0000

Data Index: 1022811 (The Pile)

Max Activating Token Index: 376