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

Dataset: The Pile

Neuron 156 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: 2.5335. Min Range: -2.5335

Max Act: 2.5335. Min Act: -0.0000

Data Index: 547160 (The Pile)

Max Activating Token Index: 715

Text #1

Max Range: 2.5335. Min Range: -2.5335

Max Act: 2.5110. Min Act: -0.0000

Data Index: 93638 (The Pile)

Max Activating Token Index: 711

Text #2

Max Range: 2.5335. Min Range: -2.5335

Max Act: 2.3272. Min Act: -0.0000

Data Index: 1053397 (The Pile)

Max Activating Token Index: 272

Text #3

Max Range: 2.5335. Min Range: -2.5335

Max Act: 2.4403. Min Act: -0.0000

Data Index: 92418 (The Pile)

Max Activating Token Index: 30

Text #4

Max Range: 2.5335. Min Range: -2.5335

Max Act: 2.2943. Min Act: -0.0000

Data Index: 1010595 (The Pile)

Max Activating Token Index: 362

Text #5

Max Range: 2.5335. Min Range: -2.5335

Max Act: 2.0603. Min Act: -0.0000

Data Index: 253921 (The Pile)

Max Activating Token Index: 858

Text #6

Max Range: 2.5335. Min Range: -2.5335

Max Act: 2.0335. Min Act: -0.0000

Data Index: 734157 (The Pile)

Max Activating Token Index: 1005

Text #7

Max Range: 2.5335. Min Range: -2.5335

Max Act: 2.1303. Min Act: -0.0000

Data Index: 1330763 (The Pile)

Max Activating Token Index: 844

Text #8

Max Range: 2.5335. Min Range: -2.5335

Max Act: 2.0258. Min Act: -0.0000

Data Index: 1405591 (The Pile)

Max Activating Token Index: 284

Text #9

Max Range: 2.5335. Min Range: -2.5335

Max Act: 1.8912. Min Act: -0.0000

Data Index: 516171 (The Pile)

Max Activating Token Index: 484

Text #10

Max Range: 2.5335. Min Range: -2.5335

Max Act: 1.9563. Min Act: -0.0000

Data Index: 1437676 (The Pile)

Max Activating Token Index: 955

Text #11

Max Range: 2.5335. Min Range: -2.5335

Max Act: 1.9412. Min Act: -0.0000

Data Index: 1531788 (The Pile)

Max Activating Token Index: 498

Text #12

Max Range: 2.5335. Min Range: -2.5335

Max Act: 2.0081. Min Act: -0.0000

Data Index: 749038 (The Pile)

Max Activating Token Index: 223

Text #13

Max Range: 2.5335. Min Range: -2.5335

Max Act: 1.7679. Min Act: -0.0000

Data Index: 1840026 (The Pile)

Max Activating Token Index: 243

Text #14

Max Range: 2.5335. Min Range: -2.5335

Max Act: 1.8437. Min Act: -0.0000

Data Index: 1860167 (The Pile)

Max Activating Token Index: 929

Text #15

Max Range: 2.5335. Min Range: -2.5335

Max Act: 1.8268. Min Act: -0.0000

Data Index: 354301 (The Pile)

Max Activating Token Index: 270

Text #16

Max Range: 2.5335. Min Range: -2.5335

Max Act: 1.8939. Min Act: -0.0000

Data Index: 12740 (The Pile)

Max Activating Token Index: 141

Text #17

Max Range: 2.5335. Min Range: -2.5335

Max Act: 1.7340. Min Act: -0.0000

Data Index: 408530 (The Pile)

Max Activating Token Index: 217

Text #18

Max Range: 2.5335. Min Range: -2.5335

Max Act: 1.7290. Min Act: -0.0000

Data Index: 1066212 (The Pile)

Max Activating Token Index: 1019

Text #19

Max Range: 2.5335. Min Range: -2.5335

Max Act: 1.7963. Min Act: -0.0000

Data Index: 328471 (The Pile)

Max Activating Token Index: 589