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

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

Neuron 1441 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.0761. Min Range: -4.0761

Max Act: 4.0761. Min Act: -0.0000

Data Index: 685529 (C4 (Web Text))

Max Activating Token Index: 173

Text #1

Max Range: 4.0761. Min Range: -4.0761

Max Act: 3.9427. Min Act: -0.0000

Data Index: 1000826 (C4 (Web Text))

Max Activating Token Index: 197

Text #2

Max Range: 4.0761. Min Range: -4.0761

Max Act: 3.8702. Min Act: -0.0000

Data Index: 1145521 (C4 (Web Text))

Max Activating Token Index: 224

Text #3

Max Range: 4.0761. Min Range: -4.0761

Max Act: 3.8197. Min Act: -0.0000

Data Index: 447932 (C4 (Web Text))

Max Activating Token Index: 209

Text #4

Max Range: 4.0761. Min Range: -4.0761

Max Act: 3.6064. Min Act: -0.0000

Data Index: 1026639 (C4 (Web Text))

Max Activating Token Index: 459

Text #5

Max Range: 4.0761. Min Range: -4.0761

Max Act: 3.2760. Min Act: -0.0000

Data Index: 1010835 (C4 (Web Text))

Max Activating Token Index: 288

Text #6

Max Range: 4.0761. Min Range: -4.0761

Max Act: 3.5570. Min Act: -0.0000

Data Index: 138185 (C4 (Web Text))

Max Activating Token Index: 567

Text #7

Max Range: 4.0761. Min Range: -4.0761

Max Act: 3.3229. Min Act: -0.0000

Data Index: 34361 (C4 (Web Text))

Max Activating Token Index: 598

Text #8

Max Range: 4.0761. Min Range: -4.0761

Max Act: 3.1490. Min Act: -0.0000

Data Index: 1165107 (C4 (Web Text))

Max Activating Token Index: 58

Text #9

Max Range: 4.0761. Min Range: -4.0761

Max Act: 3.2564. Min Act: -0.0000

Data Index: 821337 (C4 (Web Text))

Max Activating Token Index: 824

Text #10

Max Range: 4.0761. Min Range: -4.0761

Max Act: 2.7232. Min Act: -0.0000

Data Index: 130243 (C4 (Web Text))

Max Activating Token Index: 990

Text #11

Max Range: 4.0761. Min Range: -4.0761

Max Act: 2.1800. Min Act: -0.0000

Data Index: 633082 (C4 (Web Text))

Max Activating Token Index: 647

Text #12

Max Range: 4.0761. Min Range: -4.0761

Max Act: 1.9420. Min Act: -0.0000

Data Index: 1173061 (C4 (Web Text))

Max Activating Token Index: 677

Text #13

Max Range: 4.0761. Min Range: -4.0761

Max Act: 1.8198. Min Act: -0.0000

Data Index: 924367 (C4 (Web Text))

Max Activating Token Index: 130

Text #14

Max Range: 4.0761. Min Range: -4.0761

Max Act: 1.6833. Min Act: -0.0000

Data Index: 1341992 (C4 (Web Text))

Max Activating Token Index: 114

Text #15

Max Range: 4.0761. Min Range: -4.0761

Max Act: 1.6803. Min Act: -0.0000

Data Index: 1641066 (Python Code)

Max Activating Token Index: 760

Text #16

Max Range: 4.0761. Min Range: -4.0761

Max Act: 1.5702. Min Act: -0.0000

Data Index: 276583 (C4 (Web Text))

Max Activating Token Index: 659

Text #17

Max Range: 4.0761. Min Range: -4.0761

Max Act: 1.4738. Min Act: -0.0000

Data Index: 439285 (C4 (Web Text))

Max Activating Token Index: 104

Text #18

Max Range: 4.0761. Min Range: -4.0761

Max Act: 1.4592. Min Act: -0.0000

Data Index: 710086 (C4 (Web Text))

Max Activating Token Index: 119

Text #19

Max Range: 4.0761. Min Range: -4.0761

Max Act: 1.5388. Min Act: -0.0000

Data Index: 656137 (C4 (Web Text))

Max Activating Token Index: 787