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

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

Neuron 3092 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: 0.5465. Min Range: -0.5465

Max Act: 0.5465. Min Act: -0.0000

Data Index: 1418 (C4 (Web Text))

Max Activating Token Index: 699

Text #1

Max Range: 0.5465. Min Range: -0.5465

Max Act: 0.5379. Min Act: -0.0000

Data Index: 5266 (C4 (Web Text))

Max Activating Token Index: 270

Text #2

Max Range: 0.5465. Min Range: -0.5465

Max Act: 0.5437. Min Act: -0.0000

Data Index: 191254 (C4 (Web Text))

Max Activating Token Index: 110

Text #3

Max Range: 0.5465. Min Range: -0.5465

Max Act: 0.5162. Min Act: -0.0000

Data Index: 748425 (C4 (Web Text))

Max Activating Token Index: 88

Text #4

Max Range: 0.5465. Min Range: -0.5465

Max Act: 0.4942. Min Act: -0.0000

Data Index: 181092 (C4 (Web Text))

Max Activating Token Index: 798

Text #5

Max Range: 0.5465. Min Range: -0.5465

Max Act: 0.5033. Min Act: -0.0000

Data Index: 739628 (C4 (Web Text))

Max Activating Token Index: 133

Text #6

Max Range: 0.5465. Min Range: -0.5465

Max Act: 0.4927. Min Act: -0.0000

Data Index: 1135962 (C4 (Web Text))

Max Activating Token Index: 948

Text #7

Max Range: 0.5465. Min Range: -0.5465

Max Act: 0.5180. Min Act: -0.0000

Data Index: 220299 (C4 (Web Text))

Max Activating Token Index: 111

Text #8

Max Range: 0.5465. Min Range: -0.5465

Max Act: 0.4604. Min Act: -0.0000

Data Index: 147526 (C4 (Web Text))

Max Activating Token Index: 223

Text #9

Max Range: 0.5465. Min Range: -0.5465

Max Act: 0.4731. Min Act: -0.0000

Data Index: 292442 (C4 (Web Text))

Max Activating Token Index: 440

Text #10

Max Range: 0.5465. Min Range: -0.5465

Max Act: 0.4491. Min Act: -0.0000

Data Index: 305421 (C4 (Web Text))

Max Activating Token Index: 36

Text #11

Max Range: 0.5465. Min Range: -0.5465

Max Act: 0.4397. Min Act: -0.0000

Data Index: 674199 (C4 (Web Text))

Max Activating Token Index: 552

Text #12

Max Range: 0.5465. Min Range: -0.5465

Max Act: 0.4646. Min Act: -0.0000

Data Index: 607341 (C4 (Web Text))

Max Activating Token Index: 505

Text #13

Max Range: 0.5465. Min Range: -0.5465

Max Act: 0.4297. Min Act: -0.0000

Data Index: 1086218 (C4 (Web Text))

Max Activating Token Index: 100

Text #14

Max Range: 0.5465. Min Range: -0.5465

Max Act: 0.4593. Min Act: -0.0000

Data Index: 372616 (C4 (Web Text))

Max Activating Token Index: 277

Text #15

Max Range: 0.5465. Min Range: -0.5465

Max Act: 0.4585. Min Act: -0.0000

Data Index: 739746 (C4 (Web Text))

Max Activating Token Index: 534

Text #16

Max Range: 0.5465. Min Range: -0.5465

Max Act: 0.4682. Min Act: -0.0000

Data Index: 852099 (C4 (Web Text))

Max Activating Token Index: 106

Text #17

Max Range: 0.5465. Min Range: -0.5465

Max Act: 0.4228. Min Act: -0.0000

Data Index: 633216 (C4 (Web Text))

Max Activating Token Index: 634

Text #18

Max Range: 0.5465. Min Range: -0.5465

Max Act: 0.4406. Min Act: -0.0000

Data Index: 139884 (C4 (Web Text))

Max Activating Token Index: 873

Text #19

Max Range: 0.5465. Min Range: -0.5465

Max Act: 0.4083. Min Act: -0.0000

Data Index: 230616 (C4 (Web Text))

Max Activating Token Index: 619