Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 1846 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.6489. Min Range: -1.6489

Max Act: 1.6489. Min Act: -0.0000

Data Index: 286634 (The Pile)

Max Activating Token Index: 800

Text #1

Max Range: 1.6489. Min Range: -1.6489

Max Act: 1.4509. Min Act: -0.0000

Data Index: 763391 (The Pile)

Max Activating Token Index: 12

Text #2

Max Range: 1.6489. Min Range: -1.6489

Max Act: 1.4029. Min Act: -0.0000

Data Index: 1759204 (The Pile)

Max Activating Token Index: 898

Text #3

Max Range: 1.6489. Min Range: -1.6489

Max Act: 1.4056. Min Act: -0.0000

Data Index: 1715424 (The Pile)

Max Activating Token Index: 818

Text #4

Max Range: 1.6489. Min Range: -1.6489

Max Act: 1.3234. Min Act: -0.0000

Data Index: 777522 (The Pile)

Max Activating Token Index: 91

Text #5

Max Range: 1.6489. Min Range: -1.6489

Max Act: 1.4133. Min Act: -0.0000

Data Index: 774170 (The Pile)

Max Activating Token Index: 933

Text #6

Max Range: 1.6489. Min Range: -1.6489

Max Act: 1.3389. Min Act: -0.0000

Data Index: 49328 (The Pile)

Max Activating Token Index: 678

Text #7

Max Range: 1.6489. Min Range: -1.6489

Max Act: 1.3248. Min Act: -0.0000

Data Index: 712209 (The Pile)

Max Activating Token Index: 5

Text #8

Max Range: 1.6489. Min Range: -1.6489

Max Act: 1.2939. Min Act: -0.0000

Data Index: 480704 (The Pile)

Max Activating Token Index: 869

Text #9

Max Range: 1.6489. Min Range: -1.6489

Max Act: 1.2439. Min Act: -0.0000

Data Index: 1940448 (The Pile)

Max Activating Token Index: 71

Text #10

Max Range: 1.6489. Min Range: -1.6489

Max Act: 1.2880. Min Act: -0.0000

Data Index: 1925654 (The Pile)

Max Activating Token Index: 953

Text #11

Max Range: 1.6489. Min Range: -1.6489

Max Act: 1.0936. Min Act: -0.0000

Data Index: 680618 (The Pile)

Max Activating Token Index: 676

Text #12

Max Range: 1.6489. Min Range: -1.6489

Max Act: 1.1156. Min Act: -0.0000

Data Index: 959036 (The Pile)

Max Activating Token Index: 187

Text #13

Max Range: 1.6489. Min Range: -1.6489

Max Act: 1.2578. Min Act: -0.0000

Data Index: 1061130 (The Pile)

Max Activating Token Index: 50

Text #14

Max Range: 1.6489. Min Range: -1.6489

Max Act: 1.1867. Min Act: -0.0000

Data Index: 557786 (The Pile)

Max Activating Token Index: 929

Text #15

Max Range: 1.6489. Min Range: -1.6489

Max Act: 1.2398. Min Act: -0.0000

Data Index: 1075616 (The Pile)

Max Activating Token Index: 412

Text #16

Max Range: 1.6489. Min Range: -1.6489

Max Act: 1.3085. Min Act: -0.0000

Data Index: 1959226 (The Pile)

Max Activating Token Index: 510

Text #17

Max Range: 1.6489. Min Range: -1.6489

Max Act: 1.2256. Min Act: -0.0000

Data Index: 1632563 (The Pile)

Max Activating Token Index: 481

Text #18

Max Range: 1.6489. Min Range: -1.6489

Max Act: 1.1686. Min Act: -0.0000

Data Index: 690088 (The Pile)

Max Activating Token Index: 192

Text #19

Max Range: 1.6489. Min Range: -1.6489

Max Act: 1.2304. Min Act: -0.0000

Data Index: 1384146 (The Pile)

Max Activating Token Index: 406