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

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

Neuron 643 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8495. Min Range: -1.8495

Max Act: 1.8495. Min Act: -0.0000

Data Index: 188724 (C4 (Web Text))

Max Activating Token Index: 818

Text #1

Max Range: 1.8495. Min Range: -1.8495

Max Act: 1.6227. Min Act: -0.0000

Data Index: 281435 (C4 (Web Text))

Max Activating Token Index: 44

Text #2

Max Range: 1.8495. Min Range: -1.8495

Max Act: 1.5578. Min Act: -0.0000

Data Index: 370065 (C4 (Web Text))

Max Activating Token Index: 122

Text #3

Max Range: 1.8495. Min Range: -1.8495

Max Act: 1.4408. Min Act: -0.0000

Data Index: 484206 (C4 (Web Text))

Max Activating Token Index: 314

Text #4

Max Range: 1.8495. Min Range: -1.8495

Max Act: 1.4257. Min Act: -0.0000

Data Index: 592918 (C4 (Web Text))

Max Activating Token Index: 1013

Text #5

Max Range: 1.8495. Min Range: -1.8495

Max Act: 1.4027. Min Act: -0.0000

Data Index: 1045426 (C4 (Web Text))

Max Activating Token Index: 230

Text #6

Max Range: 1.8495. Min Range: -1.8495

Max Act: 1.4438. Min Act: -0.0000

Data Index: 1013245 (C4 (Web Text))

Max Activating Token Index: 283

Text #7

Max Range: 1.8495. Min Range: -1.8495

Max Act: 1.3527. Min Act: -0.0001

Data Index: 754029 (C4 (Web Text))

Max Activating Token Index: 995

Text #8

Max Range: 1.8495. Min Range: -1.8495

Max Act: 1.3885. Min Act: -0.0001

Data Index: 220513 (C4 (Web Text))

Max Activating Token Index: 887

Text #9

Max Range: 1.8495. Min Range: -1.8495

Max Act: 1.4172. Min Act: -0.0001

Data Index: 161891 (C4 (Web Text))

Max Activating Token Index: 705

Text #10

Max Range: 1.8495. Min Range: -1.8495

Max Act: 1.3320. Min Act: -0.0000

Data Index: 995104 (C4 (Web Text))

Max Activating Token Index: 409

Text #11

Max Range: 1.8495. Min Range: -1.8495

Max Act: 1.4051. Min Act: -0.0001

Data Index: 1060081 (C4 (Web Text))

Max Activating Token Index: 430

Text #12

Max Range: 1.8495. Min Range: -1.8495

Max Act: 1.3684. Min Act: -0.0000

Data Index: 142055 (C4 (Web Text))

Max Activating Token Index: 18

Text #13

Max Range: 1.8495. Min Range: -1.8495

Max Act: 1.3176. Min Act: -0.0000

Data Index: 1204241 (C4 (Web Text))

Max Activating Token Index: 880

Text #14

Max Range: 1.8495. Min Range: -1.8495

Max Act: 1.3935. Min Act: -0.0001

Data Index: 1358989 (C4 (Web Text))

Max Activating Token Index: 1007

Text #15

Max Range: 1.8495. Min Range: -1.8495

Max Act: 1.3886. Min Act: -0.0000

Data Index: 193154 (C4 (Web Text))

Max Activating Token Index: 924

Text #16

Max Range: 1.8495. Min Range: -1.8495

Max Act: 1.2962. Min Act: -0.0000

Data Index: 210978 (C4 (Web Text))

Max Activating Token Index: 305

Text #17

Max Range: 1.8495. Min Range: -1.8495

Max Act: 1.3154. Min Act: -0.0001

Data Index: 481092 (C4 (Web Text))

Max Activating Token Index: 57

Text #18

Max Range: 1.8495. Min Range: -1.8495

Max Act: 1.3508. Min Act: -0.0001

Data Index: 273073 (C4 (Web Text))

Max Activating Token Index: 167

Text #19

Max Range: 1.8495. Min Range: -1.8495

Max Act: 1.2917. Min Act: -0.0001

Data Index: 1008694 (C4 (Web Text))

Max Activating Token Index: 886