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

Dataset: The Pile

Neuron 195 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: 0.1714. Min Range: -0.1714

Max Act: 0.1714. Min Act: -0.0000

Data Index: 1925349 (The Pile)

Max Activating Token Index: 858

Text #1

Max Range: 0.1714. Min Range: -0.1714

Max Act: 0.1480. Min Act: -0.0000

Data Index: 436604 (The Pile)

Max Activating Token Index: 739

Text #2

Max Range: 0.1714. Min Range: -0.1714

Max Act: 0.1446. Min Act: -0.0000

Data Index: 1722890 (The Pile)

Max Activating Token Index: 639

Text #3

Max Range: 0.1714. Min Range: -0.1714

Max Act: 0.1427. Min Act: -0.0000

Data Index: 557133 (The Pile)

Max Activating Token Index: 314

Text #4

Max Range: 0.1714. Min Range: -0.1714

Max Act: 0.1328. Min Act: -0.0000

Data Index: 1419709 (The Pile)

Max Activating Token Index: 743

Text #5

Max Range: 0.1714. Min Range: -0.1714

Max Act: 0.1364. Min Act: -0.0000

Data Index: 1994347 (The Pile)

Max Activating Token Index: 215

Text #6

Max Range: 0.1714. Min Range: -0.1714

Max Act: 0.1329. Min Act: -0.0000

Data Index: 1648377 (The Pile)

Max Activating Token Index: 192

Text #7

Max Range: 0.1714. Min Range: -0.1714

Max Act: 0.1288. Min Act: -0.0000

Data Index: 2754 (The Pile)

Max Activating Token Index: 443

Text #8

Max Range: 0.1714. Min Range: -0.1714

Max Act: 0.1314. Min Act: -0.0000

Data Index: 76579 (The Pile)

Max Activating Token Index: 350

Text #9

Max Range: 0.1714. Min Range: -0.1714

Max Act: 0.1303. Min Act: -0.0000

Data Index: 496715 (The Pile)

Max Activating Token Index: 951

Text #10

Max Range: 0.1714. Min Range: -0.1714

Max Act: 0.1113. Min Act: -0.0000

Data Index: 235427 (The Pile)

Max Activating Token Index: 90

Text #11

Max Range: 0.1714. Min Range: -0.1714

Max Act: 0.1253. Min Act: -0.0000

Data Index: 386422 (The Pile)

Max Activating Token Index: 578

Text #12

Max Range: 0.1714. Min Range: -0.1714

Max Act: 0.1206. Min Act: -0.0000

Data Index: 1505794 (The Pile)

Max Activating Token Index: 566

Text #13

Max Range: 0.1714. Min Range: -0.1714

Max Act: 0.1160. Min Act: -0.0000

Data Index: 1476335 (The Pile)

Max Activating Token Index: 974

Text #14

Max Range: 0.1714. Min Range: -0.1714

Max Act: 0.1229. Min Act: -0.0000

Data Index: 1282674 (The Pile)

Max Activating Token Index: 914

Text #15

Max Range: 0.1714. Min Range: -0.1714

Max Act: 0.1186. Min Act: -0.0000

Data Index: 1462656 (The Pile)

Max Activating Token Index: 540

Text #16

Max Range: 0.1714. Min Range: -0.1714

Max Act: 0.1220. Min Act: -0.0000

Data Index: 1172302 (The Pile)

Max Activating Token Index: 92

Text #17

Max Range: 0.1714. Min Range: -0.1714

Max Act: 0.1183. Min Act: -0.0000

Data Index: 1821598 (The Pile)

Max Activating Token Index: 260

Text #18

Max Range: 0.1714. Min Range: -0.1714

Max Act: 0.1084. Min Act: -0.0000

Data Index: 515586 (The Pile)

Max Activating Token Index: 675

Text #19

Max Range: 0.1714. Min Range: -0.1714

Max Act: 0.1099. Min Act: -0.0000

Data Index: 984095 (The Pile)

Max Activating Token Index: 943