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

Dataset: The Pile

Neuron 1261 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2333. Min Range: -1.2333

Max Act: 1.2333. Min Act: -0.0000

Data Index: 1785681 (The Pile)

Max Activating Token Index: 389

Text #1

Max Range: 1.2333. Min Range: -1.2333

Max Act: 1.1808. Min Act: -0.0000

Data Index: 178777 (The Pile)

Max Activating Token Index: 1020

Text #2

Max Range: 1.2333. Min Range: -1.2333

Max Act: 1.1424. Min Act: 0.0000

Data Index: 255421 (The Pile)

Max Activating Token Index: 515

Text #3

Max Range: 1.2333. Min Range: -1.2333

Max Act: 1.0395. Min Act: -0.0000

Data Index: 767871 (The Pile)

Max Activating Token Index: 311

Text #4

Max Range: 1.2333. Min Range: -1.2333

Max Act: 1.0261. Min Act: -0.0000

Data Index: 1250552 (The Pile)

Max Activating Token Index: 443

Text #5

Max Range: 1.2333. Min Range: -1.2333

Max Act: 0.9937. Min Act: -0.0000

Data Index: 745513 (The Pile)

Max Activating Token Index: 251

Text #6

Max Range: 1.2333. Min Range: -1.2333

Max Act: 0.9930. Min Act: -0.0000

Data Index: 257945 (The Pile)

Max Activating Token Index: 680

Text #7

Max Range: 1.2333. Min Range: -1.2333

Max Act: 1.0186. Min Act: -0.0000

Data Index: 1285187 (The Pile)

Max Activating Token Index: 156

Text #8

Max Range: 1.2333. Min Range: -1.2333

Max Act: 1.0090. Min Act: -0.0000

Data Index: 815236 (The Pile)

Max Activating Token Index: 258

Text #9

Max Range: 1.2333. Min Range: -1.2333

Max Act: 1.0092. Min Act: -0.0000

Data Index: 433610 (The Pile)

Max Activating Token Index: 717

Text #10

Max Range: 1.2333. Min Range: -1.2333

Max Act: 0.9589. Min Act: -0.0000

Data Index: 307255 (The Pile)

Max Activating Token Index: 68

Text #11

Max Range: 1.2333. Min Range: -1.2333

Max Act: 0.9399. Min Act: -0.0000

Data Index: 1010512 (The Pile)

Max Activating Token Index: 542

Text #12

Max Range: 1.2333. Min Range: -1.2333

Max Act: 0.9297. Min Act: -0.0000

Data Index: 1690952 (The Pile)

Max Activating Token Index: 789

Text #13

Max Range: 1.2333. Min Range: -1.2333

Max Act: 0.9252. Min Act: -0.0000

Data Index: 1325678 (The Pile)

Max Activating Token Index: 321

Text #14

Max Range: 1.2333. Min Range: -1.2333

Max Act: 0.9467. Min Act: -0.0000

Data Index: 754875 (The Pile)

Max Activating Token Index: 844

Text #15

Max Range: 1.2333. Min Range: -1.2333

Max Act: 0.9492. Min Act: -0.0000

Data Index: 1109866 (The Pile)

Max Activating Token Index: 568

Text #16

Max Range: 1.2333. Min Range: -1.2333

Max Act: 0.8611. Min Act: -0.0000

Data Index: 290980 (The Pile)

Max Activating Token Index: 677

Text #17

Max Range: 1.2333. Min Range: -1.2333

Max Act: 0.8655. Min Act: -0.0000

Data Index: 231554 (The Pile)

Max Activating Token Index: 532

Text #18

Max Range: 1.2333. Min Range: -1.2333

Max Act: 0.8787. Min Act: -0.0000

Data Index: 78927 (The Pile)

Max Activating Token Index: 186

Text #19

Max Range: 1.2333. Min Range: -1.2333

Max Act: 0.8482. Min Act: -0.0000

Data Index: 1666912 (The Pile)

Max Activating Token Index: 476