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

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

Neuron 4591 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4442. Min Range: -0.4442

Max Act: 0.4442. Min Act: 0.0000

Data Index: 754412 (C4 (Web Text))

Max Activating Token Index: 483

Text #1

Max Range: 0.4442. Min Range: -0.4442

Max Act: 0.4172. Min Act: -0.0000

Data Index: 497931 (C4 (Web Text))

Max Activating Token Index: 624

Text #2

Max Range: 0.4442. Min Range: -0.4442

Max Act: 0.4059. Min Act: 0.0001

Data Index: 732388 (C4 (Web Text))

Max Activating Token Index: 436

Text #3

Max Range: 0.4442. Min Range: -0.4442

Max Act: 0.3808. Min Act: -0.0000

Data Index: 1289607 (C4 (Web Text))

Max Activating Token Index: 285

Text #4

Max Range: 0.4442. Min Range: -0.4442

Max Act: 0.3804. Min Act: -0.0000

Data Index: 1119629 (C4 (Web Text))

Max Activating Token Index: 374

Text #5

Max Range: 0.4442. Min Range: -0.4442

Max Act: 0.3658. Min Act: 0.0000

Data Index: 1039122 (C4 (Web Text))

Max Activating Token Index: 11

Text #6

Max Range: 0.4442. Min Range: -0.4442

Max Act: 0.3637. Min Act: 0.0001

Data Index: 1273975 (C4 (Web Text))

Max Activating Token Index: 997

Text #7

Max Range: 0.4442. Min Range: -0.4442

Max Act: 0.3642. Min Act: 0.0000

Data Index: 939777 (C4 (Web Text))

Max Activating Token Index: 149

Text #8

Max Range: 0.4442. Min Range: -0.4442

Max Act: 0.3288. Min Act: 0.0001

Data Index: 300527 (C4 (Web Text))

Max Activating Token Index: 398

Text #9

Max Range: 0.4442. Min Range: -0.4442

Max Act: 0.3520. Min Act: 0.0000

Data Index: 978719 (C4 (Web Text))

Max Activating Token Index: 192

Text #10

Max Range: 0.4442. Min Range: -0.4442

Max Act: 0.3391. Min Act: 0.0000

Data Index: 1297235 (C4 (Web Text))

Max Activating Token Index: 102

Text #11

Max Range: 0.4442. Min Range: -0.4442

Max Act: 0.3302. Min Act: -0.0000

Data Index: 915154 (C4 (Web Text))

Max Activating Token Index: 94

Text #12

Max Range: 0.4442. Min Range: -0.4442

Max Act: 0.3061. Min Act: 0.0000

Data Index: 784300 (C4 (Web Text))

Max Activating Token Index: 499

Text #13

Max Range: 0.4442. Min Range: -0.4442

Max Act: 0.3175. Min Act: 0.0000

Data Index: 1097983 (C4 (Web Text))

Max Activating Token Index: 289

Text #14

Max Range: 0.4442. Min Range: -0.4442

Max Act: 0.3230. Min Act: -0.0000

Data Index: 277 (C4 (Web Text))

Max Activating Token Index: 447

Text #15

Max Range: 0.4442. Min Range: -0.4442

Max Act: 0.3154. Min Act: -0.0000

Data Index: 547633 (C4 (Web Text))

Max Activating Token Index: 905

Text #16

Max Range: 0.4442. Min Range: -0.4442

Max Act: 0.3013. Min Act: -0.0000

Data Index: 620009 (C4 (Web Text))

Max Activating Token Index: 401

Text #17

Max Range: 0.4442. Min Range: -0.4442

Max Act: 0.3170. Min Act: 0.0001

Data Index: 1019692 (C4 (Web Text))

Max Activating Token Index: 342

Text #18

Max Range: 0.4442. Min Range: -0.4442

Max Act: 0.3150. Min Act: 0.0000

Data Index: 1180374 (C4 (Web Text))

Max Activating Token Index: 100

Text #19

Max Range: 0.4442. Min Range: -0.4442

Max Act: 0.2914. Min Act: 0.0001

Data Index: 120148 (C4 (Web Text))

Max Activating Token Index: 939