Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 540 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 4.5222. Min Range: -4.5222

Max Act: 4.5222. Min Act: -0.0000

Data Index: 970675 (The Pile)

Max Activating Token Index: 138

Text #1

Max Range: 4.5222. Min Range: -4.5222

Max Act: 3.8742. Min Act: -0.0000

Data Index: 1621326 (The Pile)

Max Activating Token Index: 196

Text #2

Max Range: 4.5222. Min Range: -4.5222

Max Act: 4.0423. Min Act: -0.0000

Data Index: 879964 (The Pile)

Max Activating Token Index: 655

Text #3

Max Range: 4.5222. Min Range: -4.5222

Max Act: 4.0475. Min Act: -0.0000

Data Index: 1320669 (The Pile)

Max Activating Token Index: 461

Text #4

Max Range: 4.5222. Min Range: -4.5222

Max Act: 4.1233. Min Act: -0.0000

Data Index: 306234 (The Pile)

Max Activating Token Index: 275

Text #5

Max Range: 4.5222. Min Range: -4.5222

Max Act: 3.8476. Min Act: -0.0000

Data Index: 26814 (The Pile)

Max Activating Token Index: 456

Text #6

Max Range: 4.5222. Min Range: -4.5222

Max Act: 3.5019. Min Act: -0.0000

Data Index: 1429062 (The Pile)

Max Activating Token Index: 184

Text #7

Max Range: 4.5222. Min Range: -4.5222

Max Act: 3.6493. Min Act: -0.0000

Data Index: 819839 (The Pile)

Max Activating Token Index: 599

Text #8

Max Range: 4.5222. Min Range: -4.5222

Max Act: 3.7663. Min Act: -0.0000

Data Index: 346228 (The Pile)

Max Activating Token Index: 795

Text #9

Max Range: 4.5222. Min Range: -4.5222

Max Act: 3.4475. Min Act: -0.0000

Data Index: 1466131 (The Pile)

Max Activating Token Index: 894

Text #10

Max Range: 4.5222. Min Range: -4.5222

Max Act: 3.3347. Min Act: -0.0000

Data Index: 1681782 (The Pile)

Max Activating Token Index: 309

Text #11

Max Range: 4.5222. Min Range: -4.5222

Max Act: 3.0418. Min Act: -0.0000

Data Index: 1138123 (The Pile)

Max Activating Token Index: 862

Text #12

Max Range: 4.5222. Min Range: -4.5222

Max Act: 3.3363. Min Act: -0.0000

Data Index: 1289276 (The Pile)

Max Activating Token Index: 574

Text #13

Max Range: 4.5222. Min Range: -4.5222

Max Act: 3.0059. Min Act: -0.0000

Data Index: 98184 (The Pile)

Max Activating Token Index: 993

Text #14

Max Range: 4.5222. Min Range: -4.5222

Max Act: 3.2075. Min Act: -0.0000

Data Index: 471016 (The Pile)

Max Activating Token Index: 876

Text #15

Max Range: 4.5222. Min Range: -4.5222

Max Act: 2.8595. Min Act: -0.0000

Data Index: 1889850 (The Pile)

Max Activating Token Index: 334

Text #16

Max Range: 4.5222. Min Range: -4.5222

Max Act: 2.8147. Min Act: -0.0000

Data Index: 1146536 (The Pile)

Max Activating Token Index: 550

Text #17

Max Range: 4.5222. Min Range: -4.5222

Max Act: 2.8363. Min Act: -0.0000

Data Index: 1065906 (The Pile)

Max Activating Token Index: 737

Text #18

Max Range: 4.5222. Min Range: -4.5222

Max Act: 3.0474. Min Act: -0.0000

Data Index: 1385689 (The Pile)

Max Activating Token Index: 623

Text #19

Max Range: 4.5222. Min Range: -4.5222

Max Act: 3.0652. Min Act: -0.0000

Data Index: 1080492 (The Pile)

Max Activating Token Index: 866