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

Dataset: The Pile

Neuron 2151 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: 1.1172. Min Range: -1.1172

Max Act: 1.1172. Min Act: -0.0000

Data Index: 1950578 (The Pile)

Max Activating Token Index: 761

Text #1

Max Range: 1.1172. Min Range: -1.1172

Max Act: 1.0736. Min Act: -0.0000

Data Index: 1026479 (The Pile)

Max Activating Token Index: 32

Text #2

Max Range: 1.1172. Min Range: -1.1172

Max Act: 0.9449. Min Act: -0.0000

Data Index: 972823 (The Pile)

Max Activating Token Index: 105

Text #3

Max Range: 1.1172. Min Range: -1.1172

Max Act: 0.9398. Min Act: -0.0000

Data Index: 922844 (The Pile)

Max Activating Token Index: 497

Text #4

Max Range: 1.1172. Min Range: -1.1172

Max Act: 0.8328. Min Act: -0.0000

Data Index: 891575 (The Pile)

Max Activating Token Index: 498

Text #5

Max Range: 1.1172. Min Range: -1.1172

Max Act: 0.8282. Min Act: -0.0000

Data Index: 1793793 (The Pile)

Max Activating Token Index: 993

Text #6

Max Range: 1.1172. Min Range: -1.1172

Max Act: 0.8165. Min Act: -0.0000

Data Index: 1028256 (The Pile)

Max Activating Token Index: 534

Text #7

Max Range: 1.1172. Min Range: -1.1172

Max Act: 0.7807. Min Act: -0.0000

Data Index: 188093 (The Pile)

Max Activating Token Index: 26

Text #8

Max Range: 1.1172. Min Range: -1.1172

Max Act: 0.7807. Min Act: -0.0000

Data Index: 1713439 (The Pile)

Max Activating Token Index: 284

Text #9

Max Range: 1.1172. Min Range: -1.1172

Max Act: 0.7596. Min Act: -0.0000

Data Index: 242673 (The Pile)

Max Activating Token Index: 294

Text #10

Max Range: 1.1172. Min Range: -1.1172

Max Act: 0.7106. Min Act: -0.0000

Data Index: 1241164 (The Pile)

Max Activating Token Index: 1012

Text #11

Max Range: 1.1172. Min Range: -1.1172

Max Act: 0.7241. Min Act: -0.0000

Data Index: 1071501 (The Pile)

Max Activating Token Index: 384

Text #12

Max Range: 1.1172. Min Range: -1.1172

Max Act: 0.7204. Min Act: -0.0000

Data Index: 648663 (The Pile)

Max Activating Token Index: 471

Text #13

Max Range: 1.1172. Min Range: -1.1172

Max Act: 0.7376. Min Act: -0.0000

Data Index: 907463 (The Pile)

Max Activating Token Index: 150

Text #14

Max Range: 1.1172. Min Range: -1.1172

Max Act: 0.6964. Min Act: -0.0000

Data Index: 1891551 (The Pile)

Max Activating Token Index: 972

Text #15

Max Range: 1.1172. Min Range: -1.1172

Max Act: 0.7288. Min Act: -0.0000

Data Index: 1791710 (The Pile)

Max Activating Token Index: 439

Text #16

Max Range: 1.1172. Min Range: -1.1172

Max Act: 0.6596. Min Act: -0.0000

Data Index: 902848 (The Pile)

Max Activating Token Index: 321

Text #17

Max Range: 1.1172. Min Range: -1.1172

Max Act: 0.6792. Min Act: -0.0000

Data Index: 1634852 (The Pile)

Max Activating Token Index: 191

Text #18

Max Range: 1.1172. Min Range: -1.1172

Max Act: 0.7298. Min Act: -0.0000

Data Index: 626762 (The Pile)

Max Activating Token Index: 454

Text #19

Max Range: 1.1172. Min Range: -1.1172

Max Act: 0.7011. Min Act: -0.0000

Data Index: 1789070 (The Pile)

Max Activating Token Index: 570