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

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

Neuron 141 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: 0.2557. Min Range: -0.2557

Max Act: 0.2557. Min Act: -0.0000

Data Index: 695049 (C4 (Web Text))

Max Activating Token Index: 570

Text #1

Max Range: 0.2557. Min Range: -0.2557

Max Act: 0.2428. Min Act: -0.0001

Data Index: 234955 (C4 (Web Text))

Max Activating Token Index: 776

Text #2

Max Range: 0.2557. Min Range: -0.2557

Max Act: 0.2173. Min Act: -0.0001

Data Index: 849286 (C4 (Web Text))

Max Activating Token Index: 323

Text #3

Max Range: 0.2557. Min Range: -0.2557

Max Act: 0.2231. Min Act: -0.0000

Data Index: 1076443 (C4 (Web Text))

Max Activating Token Index: 211

Text #4

Max Range: 0.2557. Min Range: -0.2557

Max Act: 0.2094. Min Act: -0.0001

Data Index: 263146 (C4 (Web Text))

Max Activating Token Index: 233

Text #5

Max Range: 0.2557. Min Range: -0.2557

Max Act: 0.2035. Min Act: -0.0000

Data Index: 926854 (C4 (Web Text))

Max Activating Token Index: 468

Text #6

Max Range: 0.2557. Min Range: -0.2557

Max Act: 0.1963. Min Act: -0.0001

Data Index: 1424283 (Python Code)

Max Activating Token Index: 658

Text #7

Max Range: 0.2557. Min Range: -0.2557

Max Act: 0.2125. Min Act: -0.0000

Data Index: 1315428 (C4 (Web Text))

Max Activating Token Index: 452

Text #8

Max Range: 0.2557. Min Range: -0.2557

Max Act: 0.2108. Min Act: -0.0001

Data Index: 1483754 (Python Code)

Max Activating Token Index: 457

Text #9

Max Range: 0.2557. Min Range: -0.2557

Max Act: 0.2004. Min Act: -0.0001

Data Index: 1510960 (Python Code)

Max Activating Token Index: 985

Text #10

Max Range: 0.2557. Min Range: -0.2557

Max Act: 0.1988. Min Act: -0.0000

Data Index: 43644 (C4 (Web Text))

Max Activating Token Index: 476

Text #11

Max Range: 0.2557. Min Range: -0.2557

Max Act: 0.1976. Min Act: -0.0000

Data Index: 299708 (C4 (Web Text))

Max Activating Token Index: 124

Text #12

Max Range: 0.2557. Min Range: -0.2557

Max Act: 0.1886. Min Act: -0.0001

Data Index: 174217 (C4 (Web Text))

Max Activating Token Index: 1003

Text #13

Max Range: 0.2557. Min Range: -0.2557

Max Act: 0.1869. Min Act: -0.0001

Data Index: 23881 (C4 (Web Text))

Max Activating Token Index: 237

Text #14

Max Range: 0.2557. Min Range: -0.2557

Max Act: 0.1913. Min Act: -0.0001

Data Index: 1404717 (Python Code)

Max Activating Token Index: 412

Text #15

Max Range: 0.2557. Min Range: -0.2557

Max Act: 0.1976. Min Act: -0.0000

Data Index: 412032 (C4 (Web Text))

Max Activating Token Index: 145

Text #16

Max Range: 0.2557. Min Range: -0.2557

Max Act: 0.1959. Min Act: -0.0000

Data Index: 206057 (C4 (Web Text))

Max Activating Token Index: 828

Text #17

Max Range: 0.2557. Min Range: -0.2557

Max Act: 0.1886. Min Act: -0.0000

Data Index: 143793 (C4 (Web Text))

Max Activating Token Index: 72

Text #18

Max Range: 0.2557. Min Range: -0.2557

Max Act: 0.1997. Min Act: -0.0001

Data Index: 788039 (C4 (Web Text))

Max Activating Token Index: 297

Text #19

Max Range: 0.2557. Min Range: -0.2557

Max Act: 0.1865. Min Act: -0.0000

Data Index: 795542 (C4 (Web Text))

Max Activating Token Index: 942