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

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

Neuron 190 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1152. Min Range: -0.1152

Max Act: 0.1152. Min Act: -0.0001

Data Index: 581243 (C4 (Web Text))

Max Activating Token Index: 862

Text #1

Max Range: 0.1152. Min Range: -0.1152

Max Act: 0.1100. Min Act: -0.0001

Data Index: 764142 (C4 (Web Text))

Max Activating Token Index: 573

Text #2

Max Range: 0.1152. Min Range: -0.1152

Max Act: 0.1078. Min Act: -0.0002

Data Index: 918900 (C4 (Web Text))

Max Activating Token Index: 638

Text #3

Max Range: 0.1152. Min Range: -0.1152

Max Act: 0.1006. Min Act: -0.0002

Data Index: 368556 (C4 (Web Text))

Max Activating Token Index: 92

Text #4

Max Range: 0.1152. Min Range: -0.1152

Max Act: 0.1001. Min Act: -0.0001

Data Index: 1000714 (C4 (Web Text))

Max Activating Token Index: 418

Text #5

Max Range: 0.1152. Min Range: -0.1152

Max Act: 0.1000. Min Act: -0.0002

Data Index: 1016989 (C4 (Web Text))

Max Activating Token Index: 424

Text #6

Max Range: 0.1152. Min Range: -0.1152

Max Act: 0.1064. Min Act: -0.0002

Data Index: 870425 (C4 (Web Text))

Max Activating Token Index: 1003

Text #7

Max Range: 0.1152. Min Range: -0.1152

Max Act: 0.1033. Min Act: -0.0001

Data Index: 626232 (C4 (Web Text))

Max Activating Token Index: 993

Text #8

Max Range: 0.1152. Min Range: -0.1152

Max Act: 0.0980. Min Act: -0.0002

Data Index: 277241 (C4 (Web Text))

Max Activating Token Index: 468

Text #9

Max Range: 0.1152. Min Range: -0.1152

Max Act: 0.0950. Min Act: -0.0002

Data Index: 1327219 (C4 (Web Text))

Max Activating Token Index: 774

Text #10

Max Range: 0.1152. Min Range: -0.1152

Max Act: 0.0889. Min Act: -0.0001

Data Index: 1089905 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 0.1152. Min Range: -0.1152

Max Act: 0.0998. Min Act: -0.0002

Data Index: 1187391 (C4 (Web Text))

Max Activating Token Index: 432

Text #12

Max Range: 0.1152. Min Range: -0.1152

Max Act: 0.0906. Min Act: -0.0002

Data Index: 1014096 (C4 (Web Text))

Max Activating Token Index: 372

Text #13

Max Range: 0.1152. Min Range: -0.1152

Max Act: 0.0879. Min Act: -0.0002

Data Index: 593051 (C4 (Web Text))

Max Activating Token Index: 581

Text #14

Max Range: 0.1152. Min Range: -0.1152

Max Act: 0.0946. Min Act: -0.0002

Data Index: 412684 (C4 (Web Text))

Max Activating Token Index: 225

Text #15

Max Range: 0.1152. Min Range: -0.1152

Max Act: 0.0897. Min Act: -0.0002

Data Index: 456495 (C4 (Web Text))

Max Activating Token Index: 327

Text #16

Max Range: 0.1152. Min Range: -0.1152

Max Act: 0.0929. Min Act: -0.0002

Data Index: 842408 (C4 (Web Text))

Max Activating Token Index: 87

Text #17

Max Range: 0.1152. Min Range: -0.1152

Max Act: 0.0883. Min Act: -0.0002

Data Index: 730296 (C4 (Web Text))

Max Activating Token Index: 245

Text #18

Max Range: 0.1152. Min Range: -0.1152

Max Act: 0.0876. Min Act: -0.0002

Data Index: 752119 (C4 (Web Text))

Max Activating Token Index: 149

Text #19

Max Range: 0.1152. Min Range: -0.1152

Max Act: 0.0901. Min Act: -0.0001

Data Index: 713282 (C4 (Web Text))

Max Activating Token Index: 523