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

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

Neuron 4478 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7030. Min Range: -2.7030

Max Act: 2.5737. Min Act: -0.0000

Data Index: 761283 (C4 (Web Text))

Max Activating Token Index: 274

Text #1

Max Range: 2.7030. Min Range: -2.7030

Max Act: 2.3857. Min Act: -0.0000

Data Index: 1180422 (C4 (Web Text))

Max Activating Token Index: 680

Text #2

Max Range: 2.7030. Min Range: -2.7030

Max Act: 2.4970. Min Act: -0.0000

Data Index: 1168972 (C4 (Web Text))

Max Activating Token Index: 899

Text #3

Max Range: 2.7030. Min Range: -2.7030

Max Act: 2.3519. Min Act: -0.0000

Data Index: 1295201 (C4 (Web Text))

Max Activating Token Index: 980

Text #4

Max Range: 2.7030. Min Range: -2.7030

Max Act: 2.3962. Min Act: -0.0000

Data Index: 791344 (C4 (Web Text))

Max Activating Token Index: 275

Text #5

Max Range: 2.7030. Min Range: -2.7030

Max Act: 2.4486. Min Act: -0.0000

Data Index: 785488 (C4 (Web Text))

Max Activating Token Index: 245

Text #6

Max Range: 2.7030. Min Range: -2.7030

Max Act: 2.5774. Min Act: -0.0000

Data Index: 1167600 (C4 (Web Text))

Max Activating Token Index: 167

Text #7

Max Range: 2.7030. Min Range: -2.7030

Max Act: 2.7030. Min Act: -0.0000

Data Index: 1111380 (C4 (Web Text))

Max Activating Token Index: 168

Text #8

Max Range: 2.7030. Min Range: -2.7030

Max Act: 2.3742. Min Act: -0.0000

Data Index: 245284 (C4 (Web Text))

Max Activating Token Index: 234

Text #9

Max Range: 2.7030. Min Range: -2.7030

Max Act: 2.4213. Min Act: -0.0000

Data Index: 365199 (C4 (Web Text))

Max Activating Token Index: 358

Text #10

Max Range: 2.7030. Min Range: -2.7030

Max Act: 2.5630. Min Act: -0.0000

Data Index: 509819 (C4 (Web Text))

Max Activating Token Index: 303

Text #11

Max Range: 2.7030. Min Range: -2.7030

Max Act: 2.3661. Min Act: -0.0000

Data Index: 167653 (C4 (Web Text))

Max Activating Token Index: 397

Text #12

Max Range: 2.7030. Min Range: -2.7030

Max Act: 2.4047. Min Act: -0.0000

Data Index: 1025109 (C4 (Web Text))

Max Activating Token Index: 460

Text #13

Max Range: 2.7030. Min Range: -2.7030

Max Act: 2.5229. Min Act: -0.0000

Data Index: 672002 (C4 (Web Text))

Max Activating Token Index: 783

Text #14

Max Range: 2.7030. Min Range: -2.7030

Max Act: 2.2794. Min Act: -0.0000

Data Index: 916156 (C4 (Web Text))

Max Activating Token Index: 640

Text #15

Max Range: 2.7030. Min Range: -2.7030

Max Act: 2.3255. Min Act: -0.0000

Data Index: 905871 (C4 (Web Text))

Max Activating Token Index: 695

Text #16

Max Range: 2.7030. Min Range: -2.7030

Max Act: 2.3897. Min Act: -0.0000

Data Index: 1324862 (C4 (Web Text))

Max Activating Token Index: 726

Text #17

Max Range: 2.7030. Min Range: -2.7030

Max Act: 2.4837. Min Act: -0.0000

Data Index: 1156984 (C4 (Web Text))

Max Activating Token Index: 719

Text #18

Max Range: 2.7030. Min Range: -2.7030

Max Act: 2.2979. Min Act: -0.0000

Data Index: 947364 (C4 (Web Text))

Max Activating Token Index: 400

Text #19

Max Range: 2.7030. Min Range: -2.7030

Max Act: 2.3475. Min Act: -0.0000

Data Index: 1086990 (C4 (Web Text))

Max Activating Token Index: 427