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

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

Neuron 1511 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6329. Min Range: -0.6329

Max Act: 0.6329. Min Act: -0.0002

Data Index: 985932 (C4 (Web Text))

Max Activating Token Index: 361

Text #1

Max Range: 0.6329. Min Range: -0.6329

Max Act: 0.5874. Min Act: -0.0002

Data Index: 28657 (C4 (Web Text))

Max Activating Token Index: 501

Text #2

Max Range: 0.6329. Min Range: -0.6329

Max Act: 0.5324. Min Act: -0.0002

Data Index: 507687 (C4 (Web Text))

Max Activating Token Index: 440

Text #3

Max Range: 0.6329. Min Range: -0.6329

Max Act: 0.5101. Min Act: -0.0002

Data Index: 296000 (C4 (Web Text))

Max Activating Token Index: 693

Text #4

Max Range: 0.6329. Min Range: -0.6329

Max Act: 0.4757. Min Act: -0.0002

Data Index: 975511 (C4 (Web Text))

Max Activating Token Index: 855

Text #5

Max Range: 0.6329. Min Range: -0.6329

Max Act: 0.4199. Min Act: -0.0002

Data Index: 1208973 (C4 (Web Text))

Max Activating Token Index: 270

Text #6

Max Range: 0.6329. Min Range: -0.6329

Max Act: 0.4653. Min Act: -0.0002

Data Index: 1017449 (C4 (Web Text))

Max Activating Token Index: 245

Text #7

Max Range: 0.6329. Min Range: -0.6329

Max Act: 0.4974. Min Act: -0.0002

Data Index: 983429 (C4 (Web Text))

Max Activating Token Index: 513

Text #8

Max Range: 0.6329. Min Range: -0.6329

Max Act: 0.5224. Min Act: -0.0002

Data Index: 921485 (C4 (Web Text))

Max Activating Token Index: 963

Text #9

Max Range: 0.6329. Min Range: -0.6329

Max Act: 0.4349. Min Act: -0.0002

Data Index: 1148605 (C4 (Web Text))

Max Activating Token Index: 310

Text #10

Max Range: 0.6329. Min Range: -0.6329

Max Act: 0.4732. Min Act: -0.0002

Data Index: 1130520 (C4 (Web Text))

Max Activating Token Index: 949

Text #11

Max Range: 0.6329. Min Range: -0.6329

Max Act: 0.3871. Min Act: -0.0002

Data Index: 465987 (C4 (Web Text))

Max Activating Token Index: 197

Text #12

Max Range: 0.6329. Min Range: -0.6329

Max Act: 0.4461. Min Act: -0.0002

Data Index: 779452 (C4 (Web Text))

Max Activating Token Index: 203

Text #13

Max Range: 0.6329. Min Range: -0.6329

Max Act: 0.4293. Min Act: -0.0002

Data Index: 683053 (C4 (Web Text))

Max Activating Token Index: 290

Text #14

Max Range: 0.6329. Min Range: -0.6329

Max Act: 0.4880. Min Act: -0.0002

Data Index: 835864 (C4 (Web Text))

Max Activating Token Index: 138

Text #15

Max Range: 0.6329. Min Range: -0.6329

Max Act: 0.4227. Min Act: -0.0002

Data Index: 118054 (C4 (Web Text))

Max Activating Token Index: 584

Text #16

Max Range: 0.6329. Min Range: -0.6329

Max Act: 0.3873. Min Act: -0.0002

Data Index: 437827 (C4 (Web Text))

Max Activating Token Index: 111

Text #17

Max Range: 0.6329. Min Range: -0.6329

Max Act: 0.3967. Min Act: -0.0002

Data Index: 587697 (C4 (Web Text))

Max Activating Token Index: 900

Text #18

Max Range: 0.6329. Min Range: -0.6329

Max Act: 0.4369. Min Act: -0.0002

Data Index: 948617 (C4 (Web Text))

Max Activating Token Index: 120

Text #19

Max Range: 0.6329. Min Range: -0.6329

Max Act: 0.4368. Min Act: -0.0002

Data Index: 359433 (C4 (Web Text))

Max Activating Token Index: 336