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

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

Neuron 3984 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0613. Min Range: -1.0613

Max Act: 0.9812. Min Act: -0.0001

Data Index: 807759 (C4 (Web Text))

Max Activating Token Index: 161

Text #1

Max Range: 1.0613. Min Range: -1.0613

Max Act: 1.0080. Min Act: -0.0000

Data Index: 1480077 (Python Code)

Max Activating Token Index: 993

Text #2

Max Range: 1.0613. Min Range: -1.0613

Max Act: 1.0318. Min Act: -0.0001

Data Index: 1593791 (Python Code)

Max Activating Token Index: 979

Text #3

Max Range: 1.0613. Min Range: -1.0613

Max Act: 1.0110. Min Act: -0.0001

Data Index: 1512397 (Python Code)

Max Activating Token Index: 869

Text #4

Max Range: 1.0613. Min Range: -1.0613

Max Act: 1.0591. Min Act: -0.0001

Data Index: 1652724 (Python Code)

Max Activating Token Index: 353

Text #5

Max Range: 1.0613. Min Range: -1.0613

Max Act: 1.0236. Min Act: -0.0001

Data Index: 1449123 (Python Code)

Max Activating Token Index: 559

Text #6

Max Range: 1.0613. Min Range: -1.0613

Max Act: 1.0106. Min Act: -0.0001

Data Index: 634747 (C4 (Web Text))

Max Activating Token Index: 958

Text #7

Max Range: 1.0613. Min Range: -1.0613

Max Act: 0.9735. Min Act: -0.0001

Data Index: 1040612 (C4 (Web Text))

Max Activating Token Index: 583

Text #8

Max Range: 1.0613. Min Range: -1.0613

Max Act: 1.0161. Min Act: -0.0001

Data Index: 1645358 (Python Code)

Max Activating Token Index: 779

Text #9

Max Range: 1.0613. Min Range: -1.0613

Max Act: 1.0613. Min Act: -0.0001

Data Index: 1651268 (Python Code)

Max Activating Token Index: 97

Text #10

Max Range: 1.0613. Min Range: -1.0613

Max Act: 1.0002. Min Act: -0.0001

Data Index: 1484792 (Python Code)

Max Activating Token Index: 594

Text #11

Max Range: 1.0613. Min Range: -1.0613

Max Act: 0.9912. Min Act: -0.0001

Data Index: 34666 (C4 (Web Text))

Max Activating Token Index: 216

Text #12

Max Range: 1.0613. Min Range: -1.0613

Max Act: 0.8718. Min Act: -0.0001

Data Index: 160102 (C4 (Web Text))

Max Activating Token Index: 239

Text #13

Max Range: 1.0613. Min Range: -1.0613

Max Act: 0.9587. Min Act: -0.0001

Data Index: 1284540 (C4 (Web Text))

Max Activating Token Index: 648

Text #14

Max Range: 1.0613. Min Range: -1.0613

Max Act: 0.9453. Min Act: -0.0001

Data Index: 1285787 (C4 (Web Text))

Max Activating Token Index: 446

Text #15

Max Range: 1.0613. Min Range: -1.0613

Max Act: 1.0244. Min Act: -0.0001

Data Index: 1424226 (Python Code)

Max Activating Token Index: 251

Text #16

Max Range: 1.0613. Min Range: -1.0613

Max Act: 0.9064. Min Act: -0.0001

Data Index: 1559039 (Python Code)

Max Activating Token Index: 106

Text #17

Max Range: 1.0613. Min Range: -1.0613

Max Act: 0.9025. Min Act: -0.0001

Data Index: 45751 (C4 (Web Text))

Max Activating Token Index: 797

Text #18

Max Range: 1.0613. Min Range: -1.0613

Max Act: 0.8915. Min Act: -0.0001

Data Index: 618459 (C4 (Web Text))

Max Activating Token Index: 260

Text #19

Max Range: 1.0613. Min Range: -1.0613

Max Act: 0.9208. Min Act: -0.0001

Data Index: 492099 (C4 (Web Text))

Max Activating Token Index: 465