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

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

Neuron 3680 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: 2.3660. Min Range: -2.3660

Max Act: 2.3660. Min Act: -0.0000

Data Index: 333208 (C4 (Web Text))

Max Activating Token Index: 258

Text #1

Max Range: 2.3660. Min Range: -2.3660

Max Act: 1.6755. Min Act: -0.0000

Data Index: 552831 (C4 (Web Text))

Max Activating Token Index: 279

Text #2

Max Range: 2.3660. Min Range: -2.3660

Max Act: 1.8361. Min Act: -0.0000

Data Index: 87546 (C4 (Web Text))

Max Activating Token Index: 303

Text #3

Max Range: 2.3660. Min Range: -2.3660

Max Act: 1.5720. Min Act: -0.0000

Data Index: 423699 (C4 (Web Text))

Max Activating Token Index: 763

Text #4

Max Range: 2.3660. Min Range: -2.3660

Max Act: 1.6447. Min Act: -0.0000

Data Index: 388326 (C4 (Web Text))

Max Activating Token Index: 427

Text #5

Max Range: 2.3660. Min Range: -2.3660

Max Act: 1.3588. Min Act: -0.0000

Data Index: 1275155 (C4 (Web Text))

Max Activating Token Index: 432

Text #6

Max Range: 2.3660. Min Range: -2.3660

Max Act: 0.0091. Min Act: -0.0000

Data Index: 243404 (C4 (Web Text))

Max Activating Token Index: 288

Text #7

Max Range: 2.3660. Min Range: -2.3660

Max Act: 0.3983. Min Act: -0.0000

Data Index: 821938 (C4 (Web Text))

Max Activating Token Index: 986

Text #8

Max Range: 2.3660. Min Range: -2.3660

Max Act: 0.9023. Min Act: -0.0000

Data Index: 119420 (C4 (Web Text))

Max Activating Token Index: 414

Text #9

Max Range: 2.3660. Min Range: -2.3660

Max Act: 1.0353. Min Act: -0.0000

Data Index: 1108134 (C4 (Web Text))

Max Activating Token Index: 204

Text #10

Max Range: 2.3660. Min Range: -2.3660

Max Act: 0.8588. Min Act: -0.0000

Data Index: 819728 (C4 (Web Text))

Max Activating Token Index: 410

Text #11

Max Range: 2.3660. Min Range: -2.3660

Max Act: 0.8776. Min Act: -0.0000

Data Index: 958805 (C4 (Web Text))

Max Activating Token Index: 590

Text #12

Max Range: 2.3660. Min Range: -2.3660

Max Act: 0.6981. Min Act: -0.0000

Data Index: 1026952 (C4 (Web Text))

Max Activating Token Index: 1015

Text #13

Max Range: 2.3660. Min Range: -2.3660

Max Act: 0.6107. Min Act: -0.0000

Data Index: 197225 (C4 (Web Text))

Max Activating Token Index: 179

Text #14

Max Range: 2.3660. Min Range: -2.3660

Max Act: 0.7777. Min Act: -0.0000

Data Index: 370506 (C4 (Web Text))

Max Activating Token Index: 682

Text #15

Max Range: 2.3660. Min Range: -2.3660

Max Act: 0.4122. Min Act: -0.0000

Data Index: 1094987 (C4 (Web Text))

Max Activating Token Index: 657

Text #16

Max Range: 2.3660. Min Range: -2.3660

Max Act: 0.4286. Min Act: -0.0000

Data Index: 155888 (C4 (Web Text))

Max Activating Token Index: 852

Text #17

Max Range: 2.3660. Min Range: -2.3660

Max Act: 0.4621. Min Act: -0.0000

Data Index: 524734 (C4 (Web Text))

Max Activating Token Index: 439

Text #18

Max Range: 2.3660. Min Range: -2.3660

Max Act: 0.4834. Min Act: -0.0000

Data Index: 947757 (C4 (Web Text))

Max Activating Token Index: 839

Text #19

Max Range: 2.3660. Min Range: -2.3660

Max Act: 0.4692. Min Act: -0.0000

Data Index: 1312815 (C4 (Web Text))

Max Activating Token Index: 509