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

Dataset: The Pile

Neuron 3919 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1951. Min Range: -0.1951

Max Act: 0.1951. Min Act: -0.0000

Data Index: 1502031 (The Pile)

Max Activating Token Index: 206

Text #1

Max Range: 0.1951. Min Range: -0.1951

Max Act: 0.1692. Min Act: -0.0000

Data Index: 804856 (The Pile)

Max Activating Token Index: 836

Text #2

Max Range: 0.1951. Min Range: -0.1951

Max Act: 0.1492. Min Act: -0.0000

Data Index: 1126480 (The Pile)

Max Activating Token Index: 929

Text #3

Max Range: 0.1951. Min Range: -0.1951

Max Act: 0.1470. Min Act: -0.0000

Data Index: 1957834 (The Pile)

Max Activating Token Index: 130

Text #4

Max Range: 0.1951. Min Range: -0.1951

Max Act: 0.1442. Min Act: -0.0000

Data Index: 1204844 (The Pile)

Max Activating Token Index: 945

Text #5

Max Range: 0.1951. Min Range: -0.1951

Max Act: 0.1428. Min Act: -0.0000

Data Index: 488738 (The Pile)

Max Activating Token Index: 484

Text #6

Max Range: 0.1951. Min Range: -0.1951

Max Act: 0.1320. Min Act: -0.0000

Data Index: 672161 (The Pile)

Max Activating Token Index: 137

Text #7

Max Range: 0.1951. Min Range: -0.1951

Max Act: 0.1374. Min Act: -0.0000

Data Index: 1999327 (The Pile)

Max Activating Token Index: 769

Text #8

Max Range: 0.1951. Min Range: -0.1951

Max Act: 0.1401. Min Act: -0.0000

Data Index: 714456 (The Pile)

Max Activating Token Index: 157

Text #9

Max Range: 0.1951. Min Range: -0.1951

Max Act: 0.1355. Min Act: -0.0000

Data Index: 1390740 (The Pile)

Max Activating Token Index: 177

Text #10

Max Range: 0.1951. Min Range: -0.1951

Max Act: 0.1289. Min Act: -0.0000

Data Index: 1489677 (The Pile)

Max Activating Token Index: 714

Text #11

Max Range: 0.1951. Min Range: -0.1951

Max Act: 0.1300. Min Act: -0.0001

Data Index: 1746280 (The Pile)

Max Activating Token Index: 297

Text #12

Max Range: 0.1951. Min Range: -0.1951

Max Act: 0.1278. Min Act: -0.0000

Data Index: 1631469 (The Pile)

Max Activating Token Index: 968

Text #13

Max Range: 0.1951. Min Range: -0.1951

Max Act: 0.1357. Min Act: -0.0000

Data Index: 1679840 (The Pile)

Max Activating Token Index: 119

Text #14

Max Range: 0.1951. Min Range: -0.1951

Max Act: 0.1375. Min Act: -0.0000

Data Index: 1278280 (The Pile)

Max Activating Token Index: 685

Text #15

Max Range: 0.1951. Min Range: -0.1951

Max Act: 0.1291. Min Act: -0.0000

Data Index: 1926282 (The Pile)

Max Activating Token Index: 1022

Text #16

Max Range: 0.1951. Min Range: -0.1951

Max Act: 0.1324. Min Act: -0.0000

Data Index: 112187 (The Pile)

Max Activating Token Index: 401

Text #17

Max Range: 0.1951. Min Range: -0.1951

Max Act: 0.1274. Min Act: -0.0000

Data Index: 120553 (The Pile)

Max Activating Token Index: 480

Text #18

Max Range: 0.1951. Min Range: -0.1951

Max Act: 0.1217. Min Act: -0.0001

Data Index: 1069288 (The Pile)

Max Activating Token Index: 356

Text #19

Max Range: 0.1951. Min Range: -0.1951

Max Act: 0.1238. Min Act: -0.0000

Data Index: 393479 (The Pile)

Max Activating Token Index: 277