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

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

Neuron 4360 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8572. Min Range: -2.8572

Max Act: 2.8572. Min Act: -0.0000

Data Index: 1277429 (C4 (Web Text))

Max Activating Token Index: 205

Text #1

Max Range: 2.8572. Min Range: -2.8572

Max Act: 1.9658. Min Act: -0.0000

Data Index: 516464 (C4 (Web Text))

Max Activating Token Index: 811

Text #2

Max Range: 2.8572. Min Range: -2.8572

Max Act: 1.7240. Min Act: -0.0000

Data Index: 1229524 (C4 (Web Text))

Max Activating Token Index: 804

Text #3

Max Range: 2.8572. Min Range: -2.8572

Max Act: 1.7913. Min Act: -0.0000

Data Index: 1275425 (C4 (Web Text))

Max Activating Token Index: 20

Text #4

Max Range: 2.8572. Min Range: -2.8572

Max Act: 1.6823. Min Act: -0.0000

Data Index: 1043247 (C4 (Web Text))

Max Activating Token Index: 269

Text #5

Max Range: 2.8572. Min Range: -2.8572

Max Act: 1.6692. Min Act: -0.0000

Data Index: 44191 (C4 (Web Text))

Max Activating Token Index: 313

Text #6

Max Range: 2.8572. Min Range: -2.8572

Max Act: 1.5599. Min Act: -0.0000

Data Index: 1236097 (C4 (Web Text))

Max Activating Token Index: 207

Text #7

Max Range: 2.8572. Min Range: -2.8572

Max Act: 1.6947. Min Act: -0.0000

Data Index: 1199789 (C4 (Web Text))

Max Activating Token Index: 1001

Text #8

Max Range: 2.8572. Min Range: -2.8572

Max Act: 1.5731. Min Act: -0.0000

Data Index: 45115 (C4 (Web Text))

Max Activating Token Index: 781

Text #9

Max Range: 2.8572. Min Range: -2.8572

Max Act: 1.5483. Min Act: -0.0000

Data Index: 852566 (C4 (Web Text))

Max Activating Token Index: 605

Text #10

Max Range: 2.8572. Min Range: -2.8572

Max Act: 1.4644. Min Act: -0.0000

Data Index: 125806 (C4 (Web Text))

Max Activating Token Index: 243

Text #11

Max Range: 2.8572. Min Range: -2.8572

Max Act: 1.5574. Min Act: -0.0000

Data Index: 325696 (C4 (Web Text))

Max Activating Token Index: 537

Text #12

Max Range: 2.8572. Min Range: -2.8572

Max Act: 1.4662. Min Act: -0.0000

Data Index: 224902 (C4 (Web Text))

Max Activating Token Index: 99

Text #13

Max Range: 2.8572. Min Range: -2.8572

Max Act: 1.3559. Min Act: -0.0000

Data Index: 623821 (C4 (Web Text))

Max Activating Token Index: 810

Text #14

Max Range: 2.8572. Min Range: -2.8572

Max Act: 1.4060. Min Act: -0.0000

Data Index: 209723 (C4 (Web Text))

Max Activating Token Index: 828

Text #15

Max Range: 2.8572. Min Range: -2.8572

Max Act: 1.3826. Min Act: -0.0000

Data Index: 902120 (C4 (Web Text))

Max Activating Token Index: 242

Text #16

Max Range: 2.8572. Min Range: -2.8572

Max Act: 1.2993. Min Act: -0.0000

Data Index: 171076 (C4 (Web Text))

Max Activating Token Index: 199

Text #17

Max Range: 2.8572. Min Range: -2.8572

Max Act: 1.4455. Min Act: -0.0000

Data Index: 692909 (C4 (Web Text))

Max Activating Token Index: 18

Text #18

Max Range: 2.8572. Min Range: -2.8572

Max Act: 1.3741. Min Act: -0.0000

Data Index: 170813 (C4 (Web Text))

Max Activating Token Index: 905

Text #19

Max Range: 2.8572. Min Range: -2.8572

Max Act: 1.3609. Min Act: -0.0000

Data Index: 819449 (C4 (Web Text))

Max Activating Token Index: 644