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

Dataset: The Pile

Neuron 5049 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2743. Min Range: -1.2743

Max Act: 1.2743. Min Act: -0.0000

Data Index: 519335 (The Pile)

Max Activating Token Index: 399

Text #1

Max Range: 1.2743. Min Range: -1.2743

Max Act: 1.1250. Min Act: -0.0000

Data Index: 1271876 (The Pile)

Max Activating Token Index: 500

Text #2

Max Range: 1.2743. Min Range: -1.2743

Max Act: 1.1206. Min Act: -0.0000

Data Index: 1431913 (The Pile)

Max Activating Token Index: 240

Text #3

Max Range: 1.2743. Min Range: -1.2743

Max Act: 1.0338. Min Act: -0.0000

Data Index: 383831 (The Pile)

Max Activating Token Index: 121

Text #4

Max Range: 1.2743. Min Range: -1.2743

Max Act: 1.0647. Min Act: -0.0000

Data Index: 965387 (The Pile)

Max Activating Token Index: 144

Text #5

Max Range: 1.2743. Min Range: -1.2743

Max Act: 1.0202. Min Act: -0.0000

Data Index: 228905 (The Pile)

Max Activating Token Index: 185

Text #6

Max Range: 1.2743. Min Range: -1.2743

Max Act: 1.0271. Min Act: -0.0000

Data Index: 1960582 (The Pile)

Max Activating Token Index: 687

Text #7

Max Range: 1.2743. Min Range: -1.2743

Max Act: 0.9696. Min Act: -0.0000

Data Index: 1436723 (The Pile)

Max Activating Token Index: 575

Text #8

Max Range: 1.2743. Min Range: -1.2743

Max Act: 1.0829. Min Act: -0.0000

Data Index: 511184 (The Pile)

Max Activating Token Index: 326

Text #9

Max Range: 1.2743. Min Range: -1.2743

Max Act: 0.9983. Min Act: -0.0000

Data Index: 1461646 (The Pile)

Max Activating Token Index: 779

Text #10

Max Range: 1.2743. Min Range: -1.2743

Max Act: 0.9306. Min Act: -0.0000

Data Index: 100515 (The Pile)

Max Activating Token Index: 439

Text #11

Max Range: 1.2743. Min Range: -1.2743

Max Act: 0.9231. Min Act: -0.0000

Data Index: 597501 (The Pile)

Max Activating Token Index: 157

Text #12

Max Range: 1.2743. Min Range: -1.2743

Max Act: 0.9578. Min Act: -0.0000

Data Index: 687434 (The Pile)

Max Activating Token Index: 763

Text #13

Max Range: 1.2743. Min Range: -1.2743

Max Act: 0.9407. Min Act: -0.0000

Data Index: 1823241 (The Pile)

Max Activating Token Index: 443

Text #14

Max Range: 1.2743. Min Range: -1.2743

Max Act: 0.9311. Min Act: -0.0000

Data Index: 645524 (The Pile)

Max Activating Token Index: 287

Text #15

Max Range: 1.2743. Min Range: -1.2743

Max Act: 0.9329. Min Act: 0.0000

Data Index: 519874 (The Pile)

Max Activating Token Index: 64

Text #16

Max Range: 1.2743. Min Range: -1.2743

Max Act: 0.8575. Min Act: -0.0000

Data Index: 529525 (The Pile)

Max Activating Token Index: 201

Text #17

Max Range: 1.2743. Min Range: -1.2743

Max Act: 0.9616. Min Act: -0.0000

Data Index: 1483137 (The Pile)

Max Activating Token Index: 198

Text #18

Max Range: 1.2743. Min Range: -1.2743

Max Act: 0.9015. Min Act: -0.0000

Data Index: 1804764 (The Pile)

Max Activating Token Index: 56

Text #19

Max Range: 1.2743. Min Range: -1.2743

Max Act: 0.8336. Min Act: -0.0000

Data Index: 1160660 (The Pile)

Max Activating Token Index: 706