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

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

Neuron 1642 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: 1.4060. Min Range: -1.4060

Max Act: 1.4060. Min Act: -0.0001

Data Index: 1151404 (C4 (Web Text))

Max Activating Token Index: 989

Text #1

Max Range: 1.4060. Min Range: -1.4060

Max Act: 1.3203. Min Act: -0.0001

Data Index: 1084253 (C4 (Web Text))

Max Activating Token Index: 143

Text #2

Max Range: 1.4060. Min Range: -1.4060

Max Act: 1.3539. Min Act: -0.0001

Data Index: 180606 (C4 (Web Text))

Max Activating Token Index: 506

Text #3

Max Range: 1.4060. Min Range: -1.4060

Max Act: 1.2605. Min Act: -0.0000

Data Index: 345845 (C4 (Web Text))

Max Activating Token Index: 456

Text #4

Max Range: 1.4060. Min Range: -1.4060

Max Act: 1.2138. Min Act: -0.0001

Data Index: 48476 (C4 (Web Text))

Max Activating Token Index: 681

Text #5

Max Range: 1.4060. Min Range: -1.4060

Max Act: 1.2441. Min Act: -0.0000

Data Index: 1103498 (C4 (Web Text))

Max Activating Token Index: 379

Text #6

Max Range: 1.4060. Min Range: -1.4060

Max Act: 1.2765. Min Act: -0.0001

Data Index: 150876 (C4 (Web Text))

Max Activating Token Index: 985

Text #7

Max Range: 1.4060. Min Range: -1.4060

Max Act: 1.2720. Min Act: -0.0001

Data Index: 1334971 (C4 (Web Text))

Max Activating Token Index: 975

Text #8

Max Range: 1.4060. Min Range: -1.4060

Max Act: 1.1565. Min Act: -0.0001

Data Index: 1250412 (C4 (Web Text))

Max Activating Token Index: 434

Text #9

Max Range: 1.4060. Min Range: -1.4060

Max Act: 1.2725. Min Act: -0.0000

Data Index: 965157 (C4 (Web Text))

Max Activating Token Index: 636

Text #10

Max Range: 1.4060. Min Range: -1.4060

Max Act: 1.1928. Min Act: -0.0001

Data Index: 1213005 (C4 (Web Text))

Max Activating Token Index: 923

Text #11

Max Range: 1.4060. Min Range: -1.4060

Max Act: 1.2082. Min Act: -0.0001

Data Index: 29274 (C4 (Web Text))

Max Activating Token Index: 114

Text #12

Max Range: 1.4060. Min Range: -1.4060

Max Act: 1.0931. Min Act: -0.0001

Data Index: 737730 (C4 (Web Text))

Max Activating Token Index: 807

Text #13

Max Range: 1.4060. Min Range: -1.4060

Max Act: 1.2519. Min Act: -0.0000

Data Index: 374502 (C4 (Web Text))

Max Activating Token Index: 399

Text #14

Max Range: 1.4060. Min Range: -1.4060

Max Act: 1.1976. Min Act: -0.0001

Data Index: 1115646 (C4 (Web Text))

Max Activating Token Index: 909

Text #15

Max Range: 1.4060. Min Range: -1.4060

Max Act: 1.1465. Min Act: -0.0001

Data Index: 1083080 (C4 (Web Text))

Max Activating Token Index: 291

Text #16

Max Range: 1.4060. Min Range: -1.4060

Max Act: 1.2201. Min Act: -0.0001

Data Index: 421542 (C4 (Web Text))

Max Activating Token Index: 177

Text #17

Max Range: 1.4060. Min Range: -1.4060

Max Act: 1.2197. Min Act: -0.0001

Data Index: 680674 (C4 (Web Text))

Max Activating Token Index: 467

Text #18

Max Range: 1.4060. Min Range: -1.4060

Max Act: 1.1517. Min Act: -0.0001

Data Index: 729461 (C4 (Web Text))

Max Activating Token Index: 443

Text #19

Max Range: 1.4060. Min Range: -1.4060

Max Act: 1.1798. Min Act: -0.0000

Data Index: 801189 (C4 (Web Text))

Max Activating Token Index: 497