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

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

Neuron 1389 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: 0.3100. Min Range: -0.3100

Max Act: 0.3100. Min Act: -0.0001

Data Index: 323758 (C4 (Web Text))

Max Activating Token Index: 478

Text #1

Max Range: 0.3100. Min Range: -0.3100

Max Act: 0.2976. Min Act: -0.0001

Data Index: 784171 (C4 (Web Text))

Max Activating Token Index: 887

Text #2

Max Range: 0.3100. Min Range: -0.3100

Max Act: 0.2938. Min Act: -0.0000

Data Index: 854659 (C4 (Web Text))

Max Activating Token Index: 563

Text #3

Max Range: 0.3100. Min Range: -0.3100

Max Act: 0.2581. Min Act: -0.0001

Data Index: 352065 (C4 (Web Text))

Max Activating Token Index: 1007

Text #4

Max Range: 0.3100. Min Range: -0.3100

Max Act: 0.2705. Min Act: -0.0001

Data Index: 109132 (C4 (Web Text))

Max Activating Token Index: 289

Text #5

Max Range: 0.3100. Min Range: -0.3100

Max Act: 0.2581. Min Act: -0.0001

Data Index: 692291 (C4 (Web Text))

Max Activating Token Index: 1016

Text #6

Max Range: 0.3100. Min Range: -0.3100

Max Act: 0.2623. Min Act: -0.0000

Data Index: 798819 (C4 (Web Text))

Max Activating Token Index: 107

Text #7

Max Range: 0.3100. Min Range: -0.3100

Max Act: 0.2534. Min Act: -0.0000

Data Index: 1006556 (C4 (Web Text))

Max Activating Token Index: 553

Text #8

Max Range: 0.3100. Min Range: -0.3100

Max Act: 0.2533. Min Act: -0.0001

Data Index: 932505 (C4 (Web Text))

Max Activating Token Index: 46

Text #9

Max Range: 0.3100. Min Range: -0.3100

Max Act: 0.2599. Min Act: -0.0001

Data Index: 649141 (C4 (Web Text))

Max Activating Token Index: 971

Text #10

Max Range: 0.3100. Min Range: -0.3100

Max Act: 0.2451. Min Act: -0.0000

Data Index: 157792 (C4 (Web Text))

Max Activating Token Index: 235

Text #11

Max Range: 0.3100. Min Range: -0.3100

Max Act: 0.2490. Min Act: -0.0001

Data Index: 641766 (C4 (Web Text))

Max Activating Token Index: 576

Text #12

Max Range: 0.3100. Min Range: -0.3100

Max Act: 0.2441. Min Act: -0.0001

Data Index: 56190 (C4 (Web Text))

Max Activating Token Index: 87

Text #13

Max Range: 0.3100. Min Range: -0.3100

Max Act: 0.2341. Min Act: -0.0001

Data Index: 811732 (C4 (Web Text))

Max Activating Token Index: 147

Text #14

Max Range: 0.3100. Min Range: -0.3100

Max Act: 0.2259. Min Act: -0.0001

Data Index: 1028894 (C4 (Web Text))

Max Activating Token Index: 588

Text #15

Max Range: 0.3100. Min Range: -0.3100

Max Act: 0.2167. Min Act: -0.0001

Data Index: 558750 (C4 (Web Text))

Max Activating Token Index: 600

Text #16

Max Range: 0.3100. Min Range: -0.3100

Max Act: 0.2218. Min Act: -0.0000

Data Index: 1100945 (C4 (Web Text))

Max Activating Token Index: 572

Text #17

Max Range: 0.3100. Min Range: -0.3100

Max Act: 0.2200. Min Act: -0.0000

Data Index: 1173435 (C4 (Web Text))

Max Activating Token Index: 844

Text #18

Max Range: 0.3100. Min Range: -0.3100

Max Act: 0.2328. Min Act: -0.0000

Data Index: 1125297 (C4 (Web Text))

Max Activating Token Index: 173

Text #19

Max Range: 0.3100. Min Range: -0.3100

Max Act: 0.2246. Min Act: -0.0001

Data Index: 147789 (C4 (Web Text))

Max Activating Token Index: 418