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

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

Neuron 162 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8108. Min Range: -0.8108

Max Act: 0.7737. Min Act: -0.0001

Data Index: 287194 (C4 (Web Text))

Max Activating Token Index: 660

Text #1

Max Range: 0.8108. Min Range: -0.8108

Max Act: 0.8108. Min Act: -0.0001

Data Index: 660099 (C4 (Web Text))

Max Activating Token Index: 333

Text #2

Max Range: 0.8108. Min Range: -0.8108

Max Act: 0.7694. Min Act: -0.0001

Data Index: 873 (C4 (Web Text))

Max Activating Token Index: 984

Text #3

Max Range: 0.8108. Min Range: -0.8108

Max Act: 0.7780. Min Act: -0.0001

Data Index: 411194 (C4 (Web Text))

Max Activating Token Index: 465

Text #4

Max Range: 0.8108. Min Range: -0.8108

Max Act: 0.7716. Min Act: -0.0001

Data Index: 180822 (C4 (Web Text))

Max Activating Token Index: 289

Text #5

Max Range: 0.8108. Min Range: -0.8108

Max Act: 0.7444. Min Act: -0.0001

Data Index: 968208 (C4 (Web Text))

Max Activating Token Index: 140

Text #6

Max Range: 0.8108. Min Range: -0.8108

Max Act: 0.7285. Min Act: -0.0001

Data Index: 1084767 (C4 (Web Text))

Max Activating Token Index: 223

Text #7

Max Range: 0.8108. Min Range: -0.8108

Max Act: 0.7229. Min Act: -0.0001

Data Index: 8554 (C4 (Web Text))

Max Activating Token Index: 232

Text #8

Max Range: 0.8108. Min Range: -0.8108

Max Act: 0.7186. Min Act: -0.0001

Data Index: 1067773 (C4 (Web Text))

Max Activating Token Index: 236

Text #9

Max Range: 0.8108. Min Range: -0.8108

Max Act: 0.7624. Min Act: -0.0001

Data Index: 1283867 (C4 (Web Text))

Max Activating Token Index: 95

Text #10

Max Range: 0.8108. Min Range: -0.8108

Max Act: 0.7404. Min Act: -0.0001

Data Index: 1062174 (C4 (Web Text))

Max Activating Token Index: 66

Text #11

Max Range: 0.8108. Min Range: -0.8108

Max Act: 0.7094. Min Act: -0.0001

Data Index: 559659 (C4 (Web Text))

Max Activating Token Index: 288

Text #12

Max Range: 0.8108. Min Range: -0.8108

Max Act: 0.7752. Min Act: -0.0001

Data Index: 789427 (C4 (Web Text))

Max Activating Token Index: 256

Text #13

Max Range: 0.8108. Min Range: -0.8108

Max Act: 0.7427. Min Act: -0.0001

Data Index: 1083227 (C4 (Web Text))

Max Activating Token Index: 574

Text #14

Max Range: 0.8108. Min Range: -0.8108

Max Act: 0.6794. Min Act: -0.0001

Data Index: 1350505 (C4 (Web Text))

Max Activating Token Index: 990

Text #15

Max Range: 0.8108. Min Range: -0.8108

Max Act: 0.6970. Min Act: -0.0001

Data Index: 187562 (C4 (Web Text))

Max Activating Token Index: 850

Text #16

Max Range: 0.8108. Min Range: -0.8108

Max Act: 0.6363. Min Act: -0.0001

Data Index: 433876 (C4 (Web Text))

Max Activating Token Index: 812

Text #17

Max Range: 0.8108. Min Range: -0.8108

Max Act: 0.7170. Min Act: -0.0001

Data Index: 1166526 (C4 (Web Text))

Max Activating Token Index: 264

Text #18

Max Range: 0.8108. Min Range: -0.8108

Max Act: 0.7177. Min Act: -0.0001

Data Index: 880239 (C4 (Web Text))

Max Activating Token Index: 367

Text #19

Max Range: 0.8108. Min Range: -0.8108

Max Act: 0.6900. Min Act: -0.0001

Data Index: 897825 (C4 (Web Text))

Max Activating Token Index: 948