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

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

Neuron 2518 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5418. Min Range: -0.5418

Max Act: 0.5085. Min Act: -0.0001

Data Index: 610734 (C4 (Web Text))

Max Activating Token Index: 801

Text #1

Max Range: 0.5418. Min Range: -0.5418

Max Act: 0.5418. Min Act: -0.0000

Data Index: 415423 (C4 (Web Text))

Max Activating Token Index: 244

Text #2

Max Range: 0.5418. Min Range: -0.5418

Max Act: 0.5196. Min Act: -0.0001

Data Index: 1077303 (C4 (Web Text))

Max Activating Token Index: 992

Text #3

Max Range: 0.5418. Min Range: -0.5418

Max Act: 0.5323. Min Act: -0.0001

Data Index: 655126 (C4 (Web Text))

Max Activating Token Index: 490

Text #4

Max Range: 0.5418. Min Range: -0.5418

Max Act: 0.5081. Min Act: -0.0001

Data Index: 803722 (C4 (Web Text))

Max Activating Token Index: 254

Text #5

Max Range: 0.5418. Min Range: -0.5418

Max Act: 0.5056. Min Act: -0.0000

Data Index: 100051 (C4 (Web Text))

Max Activating Token Index: 522

Text #6

Max Range: 0.5418. Min Range: -0.5418

Max Act: 0.5031. Min Act: -0.0000

Data Index: 556225 (C4 (Web Text))

Max Activating Token Index: 213

Text #7

Max Range: 0.5418. Min Range: -0.5418

Max Act: 0.5001. Min Act: -0.0001

Data Index: 745008 (C4 (Web Text))

Max Activating Token Index: 267

Text #8

Max Range: 0.5418. Min Range: -0.5418

Max Act: 0.4994. Min Act: -0.0000

Data Index: 282870 (C4 (Web Text))

Max Activating Token Index: 364

Text #9

Max Range: 0.5418. Min Range: -0.5418

Max Act: 0.4945. Min Act: -0.0001

Data Index: 141872 (C4 (Web Text))

Max Activating Token Index: 484

Text #10

Max Range: 0.5418. Min Range: -0.5418

Max Act: 0.4837. Min Act: -0.0001

Data Index: 136804 (C4 (Web Text))

Max Activating Token Index: 897

Text #11

Max Range: 0.5418. Min Range: -0.5418

Max Act: 0.4765. Min Act: -0.0001

Data Index: 619880 (C4 (Web Text))

Max Activating Token Index: 87

Text #12

Max Range: 0.5418. Min Range: -0.5418

Max Act: 0.4768. Min Act: -0.0000

Data Index: 18045 (C4 (Web Text))

Max Activating Token Index: 175

Text #13

Max Range: 0.5418. Min Range: -0.5418

Max Act: 0.4881. Min Act: -0.0000

Data Index: 1073703 (C4 (Web Text))

Max Activating Token Index: 603

Text #14

Max Range: 0.5418. Min Range: -0.5418

Max Act: 0.4897. Min Act: -0.0000

Data Index: 223681 (C4 (Web Text))

Max Activating Token Index: 1000

Text #15

Max Range: 0.5418. Min Range: -0.5418

Max Act: 0.4477. Min Act: -0.0000

Data Index: 136172 (C4 (Web Text))

Max Activating Token Index: 352

Text #16

Max Range: 0.5418. Min Range: -0.5418

Max Act: 0.4638. Min Act: -0.0000

Data Index: 880261 (C4 (Web Text))

Max Activating Token Index: 992

Text #17

Max Range: 0.5418. Min Range: -0.5418

Max Act: 0.4640. Min Act: -0.0001

Data Index: 286272 (C4 (Web Text))

Max Activating Token Index: 95

Text #18

Max Range: 0.5418. Min Range: -0.5418

Max Act: 0.4599. Min Act: -0.0001

Data Index: 1043203 (C4 (Web Text))

Max Activating Token Index: 39

Text #19

Max Range: 0.5418. Min Range: -0.5418

Max Act: 0.4753. Min Act: -0.0000

Data Index: 963927 (C4 (Web Text))

Max Activating Token Index: 1008