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

Dataset: The Pile

Neuron 2900 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: 1.1296. Min Range: -1.1296

Max Act: 1.1296. Min Act: -0.0000

Data Index: 287463 (The Pile)

Max Activating Token Index: 769

Text #1

Max Range: 1.1296. Min Range: -1.1296

Max Act: 1.0323. Min Act: -0.0000

Data Index: 1547607 (The Pile)

Max Activating Token Index: 258

Text #2

Max Range: 1.1296. Min Range: -1.1296

Max Act: 0.9773. Min Act: -0.0000

Data Index: 1556613 (The Pile)

Max Activating Token Index: 926

Text #3

Max Range: 1.1296. Min Range: -1.1296

Max Act: 0.8973. Min Act: -0.0000

Data Index: 725513 (The Pile)

Max Activating Token Index: 205

Text #4

Max Range: 1.1296. Min Range: -1.1296

Max Act: 0.8787. Min Act: -0.0000

Data Index: 1429015 (The Pile)

Max Activating Token Index: 462

Text #5

Max Range: 1.1296. Min Range: -1.1296

Max Act: 0.9519. Min Act: -0.0000

Data Index: 464478 (The Pile)

Max Activating Token Index: 691

Text #6

Max Range: 1.1296. Min Range: -1.1296

Max Act: 0.8305. Min Act: -0.0000

Data Index: 1907554 (The Pile)

Max Activating Token Index: 603

Text #7

Max Range: 1.1296. Min Range: -1.1296

Max Act: 0.8165. Min Act: -0.0000

Data Index: 539044 (The Pile)

Max Activating Token Index: 908

Text #8

Max Range: 1.1296. Min Range: -1.1296

Max Act: 0.7911. Min Act: -0.0000

Data Index: 836182 (The Pile)

Max Activating Token Index: 762

Text #9

Max Range: 1.1296. Min Range: -1.1296

Max Act: 0.8172. Min Act: -0.0000

Data Index: 943737 (The Pile)

Max Activating Token Index: 799

Text #10

Max Range: 1.1296. Min Range: -1.1296

Max Act: 0.8096. Min Act: -0.0000

Data Index: 440607 (The Pile)

Max Activating Token Index: 263

Text #11

Max Range: 1.1296. Min Range: -1.1296

Max Act: 0.8008. Min Act: -0.0000

Data Index: 1160977 (The Pile)

Max Activating Token Index: 663

Text #12

Max Range: 1.1296. Min Range: -1.1296

Max Act: 0.8005. Min Act: -0.0000

Data Index: 385331 (The Pile)

Max Activating Token Index: 210

Text #13

Max Range: 1.1296. Min Range: -1.1296

Max Act: 0.7222. Min Act: -0.0000

Data Index: 1848413 (The Pile)

Max Activating Token Index: 1009

Text #14

Max Range: 1.1296. Min Range: -1.1296

Max Act: 0.7773. Min Act: -0.0000

Data Index: 1466822 (The Pile)

Max Activating Token Index: 712

Text #15

Max Range: 1.1296. Min Range: -1.1296

Max Act: 0.7982. Min Act: -0.0000

Data Index: 1468820 (The Pile)

Max Activating Token Index: 189

Text #16

Max Range: 1.1296. Min Range: -1.1296

Max Act: 0.7233. Min Act: -0.0000

Data Index: 797670 (The Pile)

Max Activating Token Index: 585

Text #17

Max Range: 1.1296. Min Range: -1.1296

Max Act: 0.7269. Min Act: -0.0000

Data Index: 574636 (The Pile)

Max Activating Token Index: 444

Text #18

Max Range: 1.1296. Min Range: -1.1296

Max Act: 0.7291. Min Act: -0.0000

Data Index: 164758 (The Pile)

Max Activating Token Index: 248

Text #19

Max Range: 1.1296. Min Range: -1.1296

Max Act: 0.7327. Min Act: -0.0000

Data Index: 440456 (The Pile)

Max Activating Token Index: 87