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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 2705 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7246. Min Range: -0.7246

Max Act: 0.7246. Min Act: -0.0000

Data Index: 282122 (C4 (Web Text))

Max Activating Token Index: 367

Text #1

Max Range: 0.7246. Min Range: -0.7246

Max Act: 0.5685. Min Act: -0.0000

Data Index: 219908 (C4 (Web Text))

Max Activating Token Index: 998

Text #2

Max Range: 0.7246. Min Range: -0.7246

Max Act: 0.4918. Min Act: -0.0000

Data Index: 69635 (C4 (Web Text))

Max Activating Token Index: 468

Text #3

Max Range: 0.7246. Min Range: -0.7246

Max Act: 0.4927. Min Act: -0.0000

Data Index: 251716 (C4 (Web Text))

Max Activating Token Index: 554

Text #4

Max Range: 0.7246. Min Range: -0.7246

Max Act: 0.4811. Min Act: -0.0000

Data Index: 678337 (C4 (Web Text))

Max Activating Token Index: 207

Text #5

Max Range: 0.7246. Min Range: -0.7246

Max Act: 0.4787. Min Act: -0.0000

Data Index: 791997 (C4 (Web Text))

Max Activating Token Index: 122

Text #6

Max Range: 0.7246. Min Range: -0.7246

Max Act: 0.4642. Min Act: -0.0000

Data Index: 166197 (C4 (Web Text))

Max Activating Token Index: 468

Text #7

Max Range: 0.7246. Min Range: -0.7246

Max Act: 0.4457. Min Act: -0.0000

Data Index: 356847 (C4 (Web Text))

Max Activating Token Index: 223

Text #8

Max Range: 0.7246. Min Range: -0.7246

Max Act: 0.4509. Min Act: -0.0000

Data Index: 1227636 (C4 (Web Text))

Max Activating Token Index: 29

Text #9

Max Range: 0.7246. Min Range: -0.7246

Max Act: 0.4094. Min Act: -0.0000

Data Index: 461988 (C4 (Web Text))

Max Activating Token Index: 999

Text #10

Max Range: 0.7246. Min Range: -0.7246

Max Act: 0.4475. Min Act: -0.0000

Data Index: 169960 (C4 (Web Text))

Max Activating Token Index: 175

Text #11

Max Range: 0.7246. Min Range: -0.7246

Max Act: 0.4304. Min Act: -0.0000

Data Index: 471315 (C4 (Web Text))

Max Activating Token Index: 429

Text #12

Max Range: 0.7246. Min Range: -0.7246

Max Act: 0.4591. Min Act: -0.0001

Data Index: 975162 (C4 (Web Text))

Max Activating Token Index: 1016

Text #13

Max Range: 0.7246. Min Range: -0.7246

Max Act: 0.4217. Min Act: -0.0000

Data Index: 251681 (C4 (Web Text))

Max Activating Token Index: 467

Text #14

Max Range: 0.7246. Min Range: -0.7246

Max Act: 0.4157. Min Act: -0.0000

Data Index: 815286 (C4 (Web Text))

Max Activating Token Index: 271

Text #15

Max Range: 0.7246. Min Range: -0.7246

Max Act: 0.4188. Min Act: -0.0000

Data Index: 335420 (C4 (Web Text))

Max Activating Token Index: 213

Text #16

Max Range: 0.7246. Min Range: -0.7246

Max Act: 0.4196. Min Act: -0.0001

Data Index: 163670 (C4 (Web Text))

Max Activating Token Index: 994

Text #17

Max Range: 0.7246. Min Range: -0.7246

Max Act: 0.4183. Min Act: -0.0000

Data Index: 797488 (C4 (Web Text))

Max Activating Token Index: 214

Text #18

Max Range: 0.7246. Min Range: -0.7246

Max Act: 0.4077. Min Act: -0.0000

Data Index: 591177 (C4 (Web Text))

Max Activating Token Index: 583

Text #19

Max Range: 0.7246. Min Range: -0.7246

Max Act: 0.3977. Min Act: -0.0001

Data Index: 573407 (C4 (Web Text))

Max Activating Token Index: 803