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

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

Neuron 3868 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7637. Min Range: -0.7637

Max Act: 0.7549. Min Act: -0.0001

Data Index: 940927 (C4 (Web Text))

Max Activating Token Index: 160

Text #1

Max Range: 0.7637. Min Range: -0.7637

Max Act: 0.7637. Min Act: -0.0001

Data Index: 734533 (C4 (Web Text))

Max Activating Token Index: 816

Text #2

Max Range: 0.7637. Min Range: -0.7637

Max Act: 0.7280. Min Act: -0.0001

Data Index: 335015 (C4 (Web Text))

Max Activating Token Index: 624

Text #3

Max Range: 0.7637. Min Range: -0.7637

Max Act: 0.6279. Min Act: -0.0001

Data Index: 1086309 (C4 (Web Text))

Max Activating Token Index: 52

Text #4

Max Range: 0.7637. Min Range: -0.7637

Max Act: 0.5341. Min Act: -0.0001

Data Index: 546252 (C4 (Web Text))

Max Activating Token Index: 684

Text #5

Max Range: 0.7637. Min Range: -0.7637

Max Act: 0.6570. Min Act: -0.0001

Data Index: 595371 (C4 (Web Text))

Max Activating Token Index: 279

Text #6

Max Range: 0.7637. Min Range: -0.7637

Max Act: 0.5928. Min Act: -0.0001

Data Index: 921156 (C4 (Web Text))

Max Activating Token Index: 892

Text #7

Max Range: 0.7637. Min Range: -0.7637

Max Act: 0.5477. Min Act: -0.0001

Data Index: 866121 (C4 (Web Text))

Max Activating Token Index: 83

Text #8

Max Range: 0.7637. Min Range: -0.7637

Max Act: 0.5099. Min Act: -0.0001

Data Index: 1294620 (C4 (Web Text))

Max Activating Token Index: 868

Text #9

Max Range: 0.7637. Min Range: -0.7637

Max Act: 0.4753. Min Act: -0.0001

Data Index: 974084 (C4 (Web Text))

Max Activating Token Index: 717

Text #10

Max Range: 0.7637. Min Range: -0.7637

Max Act: 0.5173. Min Act: -0.0001

Data Index: 416026 (C4 (Web Text))

Max Activating Token Index: 71

Text #11

Max Range: 0.7637. Min Range: -0.7637

Max Act: 0.5457. Min Act: -0.0001

Data Index: 178402 (C4 (Web Text))

Max Activating Token Index: 677

Text #12

Max Range: 0.7637. Min Range: -0.7637

Max Act: 0.5441. Min Act: -0.0001

Data Index: 249896 (C4 (Web Text))

Max Activating Token Index: 418

Text #13

Max Range: 0.7637. Min Range: -0.7637

Max Act: 0.5256. Min Act: -0.0001

Data Index: 254481 (C4 (Web Text))

Max Activating Token Index: 14

Text #14

Max Range: 0.7637. Min Range: -0.7637

Max Act: 0.5270. Min Act: -0.0001

Data Index: 1111837 (C4 (Web Text))

Max Activating Token Index: 489

Text #15

Max Range: 0.7637. Min Range: -0.7637

Max Act: 0.4894. Min Act: -0.0001

Data Index: 251847 (C4 (Web Text))

Max Activating Token Index: 248

Text #16

Max Range: 0.7637. Min Range: -0.7637

Max Act: 0.5166. Min Act: -0.0001

Data Index: 385837 (C4 (Web Text))

Max Activating Token Index: 1015

Text #17

Max Range: 0.7637. Min Range: -0.7637

Max Act: 0.4994. Min Act: -0.0001

Data Index: 819374 (C4 (Web Text))

Max Activating Token Index: 169

Text #18

Max Range: 0.7637. Min Range: -0.7637

Max Act: 0.5021. Min Act: -0.0001

Data Index: 601539 (C4 (Web Text))

Max Activating Token Index: 901

Text #19

Max Range: 0.7637. Min Range: -0.7637

Max Act: 0.4907. Min Act: -0.0001

Data Index: 1321528 (C4 (Web Text))

Max Activating Token Index: 5