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

Dataset: The Pile

Neuron 4782 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: 0.9982. Min Range: -0.9982

Max Act: 0.9527. Min Act: -0.0000

Data Index: 1613505 (The Pile)

Max Activating Token Index: 677

Text #1

Max Range: 0.9982. Min Range: -0.9982

Max Act: 0.8907. Min Act: -0.0000

Data Index: 1091041 (The Pile)

Max Activating Token Index: 565

Text #2

Max Range: 0.9982. Min Range: -0.9982

Max Act: 0.9141. Min Act: -0.0000

Data Index: 1160976 (The Pile)

Max Activating Token Index: 163

Text #3

Max Range: 0.9982. Min Range: -0.9982

Max Act: 0.9982. Min Act: -0.0000

Data Index: 1732466 (The Pile)

Max Activating Token Index: 572

Text #4

Max Range: 0.9982. Min Range: -0.9982

Max Act: 0.9771. Min Act: -0.0000

Data Index: 226726 (The Pile)

Max Activating Token Index: 682

Text #5

Max Range: 0.9982. Min Range: -0.9982

Max Act: 0.8623. Min Act: -0.0000

Data Index: 52939 (The Pile)

Max Activating Token Index: 508

Text #6

Max Range: 0.9982. Min Range: -0.9982

Max Act: 0.9048. Min Act: -0.0000

Data Index: 1859705 (The Pile)

Max Activating Token Index: 210

Text #7

Max Range: 0.9982. Min Range: -0.9982

Max Act: 0.9127. Min Act: -0.0000

Data Index: 1239551 (The Pile)

Max Activating Token Index: 559

Text #8

Max Range: 0.9982. Min Range: -0.9982

Max Act: 0.8822. Min Act: -0.0000

Data Index: 1602875 (The Pile)

Max Activating Token Index: 390

Text #9

Max Range: 0.9982. Min Range: -0.9982

Max Act: 0.8661. Min Act: -0.0000

Data Index: 1809146 (The Pile)

Max Activating Token Index: 833

Text #10

Max Range: 0.9982. Min Range: -0.9982

Max Act: 0.7831. Min Act: -0.0000

Data Index: 1219618 (The Pile)

Max Activating Token Index: 1017

Text #11

Max Range: 0.9982. Min Range: -0.9982

Max Act: 0.8575. Min Act: -0.0000

Data Index: 1097019 (The Pile)

Max Activating Token Index: 58

Text #12

Max Range: 0.9982. Min Range: -0.9982

Max Act: 0.8430. Min Act: -0.0000

Data Index: 237764 (The Pile)

Max Activating Token Index: 598

Text #13

Max Range: 0.9982. Min Range: -0.9982

Max Act: 0.8127. Min Act: -0.0000

Data Index: 1281248 (The Pile)

Max Activating Token Index: 371

Text #14

Max Range: 0.9982. Min Range: -0.9982

Max Act: 0.8184. Min Act: -0.0000

Data Index: 1912442 (The Pile)

Max Activating Token Index: 319

Text #15

Max Range: 0.9982. Min Range: -0.9982

Max Act: 0.7808. Min Act: -0.0000

Data Index: 1316912 (The Pile)

Max Activating Token Index: 447

Text #16

Max Range: 0.9982. Min Range: -0.9982

Max Act: 0.8279. Min Act: -0.0000

Data Index: 1912952 (The Pile)

Max Activating Token Index: 328

Text #17

Max Range: 0.9982. Min Range: -0.9982

Max Act: 0.8062. Min Act: -0.0000

Data Index: 156669 (The Pile)

Max Activating Token Index: 950

Text #18

Max Range: 0.9982. Min Range: -0.9982

Max Act: 0.8238. Min Act: -0.0000

Data Index: 920373 (The Pile)

Max Activating Token Index: 621

Text #19

Max Range: 0.9982. Min Range: -0.9982

Max Act: 0.7724. Min Act: -0.0000

Data Index: 397248 (The Pile)

Max Activating Token Index: 425