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

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

Neuron 964 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5174. Min Range: -0.5174

Max Act: 0.5174. Min Act: -0.0000

Data Index: 587912 (C4 (Web Text))

Max Activating Token Index: 95

Text #1

Max Range: 0.5174. Min Range: -0.5174

Max Act: 0.4913. Min Act: -0.0000

Data Index: 1536976 (Python Code)

Max Activating Token Index: 142

Text #2

Max Range: 0.5174. Min Range: -0.5174

Max Act: 0.4602. Min Act: -0.0000

Data Index: 224066 (C4 (Web Text))

Max Activating Token Index: 339

Text #3

Max Range: 0.5174. Min Range: -0.5174

Max Act: 0.4719. Min Act: -0.0000

Data Index: 1288872 (C4 (Web Text))

Max Activating Token Index: 12

Text #4

Max Range: 0.5174. Min Range: -0.5174

Max Act: 0.4227. Min Act: -0.0000

Data Index: 518138 (C4 (Web Text))

Max Activating Token Index: 192

Text #5

Max Range: 0.5174. Min Range: -0.5174

Max Act: 0.5036. Min Act: -0.0000

Data Index: 1135376 (C4 (Web Text))

Max Activating Token Index: 218

Text #6

Max Range: 0.5174. Min Range: -0.5174

Max Act: 0.4296. Min Act: -0.0000

Data Index: 304148 (C4 (Web Text))

Max Activating Token Index: 466

Text #7

Max Range: 0.5174. Min Range: -0.5174

Max Act: 0.3888. Min Act: -0.0000

Data Index: 447706 (C4 (Web Text))

Max Activating Token Index: 530

Text #8

Max Range: 0.5174. Min Range: -0.5174

Max Act: 0.3634. Min Act: -0.0000

Data Index: 1247972 (C4 (Web Text))

Max Activating Token Index: 367

Text #9

Max Range: 0.5174. Min Range: -0.5174

Max Act: 0.3799. Min Act: -0.0000

Data Index: 935740 (C4 (Web Text))

Max Activating Token Index: 1008

Text #10

Max Range: 0.5174. Min Range: -0.5174

Max Act: 0.3189. Min Act: -0.0000

Data Index: 1134115 (C4 (Web Text))

Max Activating Token Index: 412

Text #11

Max Range: 0.5174. Min Range: -0.5174

Max Act: 0.3538. Min Act: -0.0000

Data Index: 1083507 (C4 (Web Text))

Max Activating Token Index: 95

Text #12

Max Range: 0.5174. Min Range: -0.5174

Max Act: 0.3454. Min Act: -0.0000

Data Index: 1602422 (Python Code)

Max Activating Token Index: 722

Text #13

Max Range: 0.5174. Min Range: -0.5174

Max Act: 0.3210. Min Act: -0.0000

Data Index: 518849 (C4 (Web Text))

Max Activating Token Index: 640

Text #14

Max Range: 0.5174. Min Range: -0.5174

Max Act: 0.3176. Min Act: -0.0000

Data Index: 239867 (C4 (Web Text))

Max Activating Token Index: 558

Text #15

Max Range: 0.5174. Min Range: -0.5174

Max Act: 0.3176. Min Act: -0.0000

Data Index: 528213 (C4 (Web Text))

Max Activating Token Index: 409

Text #16

Max Range: 0.5174. Min Range: -0.5174

Max Act: 0.3012. Min Act: -0.0000

Data Index: 160545 (C4 (Web Text))

Max Activating Token Index: 153

Text #17

Max Range: 0.5174. Min Range: -0.5174

Max Act: 0.2948. Min Act: -0.0000

Data Index: 62750 (C4 (Web Text))

Max Activating Token Index: 840

Text #18

Max Range: 0.5174. Min Range: -0.5174

Max Act: 0.3050. Min Act: -0.0000

Data Index: 912349 (C4 (Web Text))

Max Activating Token Index: 108

Text #19

Max Range: 0.5174. Min Range: -0.5174

Max Act: 0.2921. Min Act: -0.0000

Data Index: 796158 (C4 (Web Text))

Max Activating Token Index: 849