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

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

Neuron 412 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1461. Min Range: -0.1461

Max Act: 0.1461. Min Act: -0.0001

Data Index: 116775 (C4 (Web Text))

Max Activating Token Index: 418

Text #1

Max Range: 0.1461. Min Range: -0.1461

Max Act: 0.1305. Min Act: -0.0001

Data Index: 1033232 (C4 (Web Text))

Max Activating Token Index: 758

Text #2

Max Range: 0.1461. Min Range: -0.1461

Max Act: 0.1276. Min Act: -0.0001

Data Index: 1477904 (Python Code)

Max Activating Token Index: 382

Text #3

Max Range: 0.1461. Min Range: -0.1461

Max Act: 0.1168. Min Act: -0.0000

Data Index: 876157 (C4 (Web Text))

Max Activating Token Index: 909

Text #4

Max Range: 0.1461. Min Range: -0.1461

Max Act: 0.1157. Min Act: -0.0000

Data Index: 1030627 (C4 (Web Text))

Max Activating Token Index: 177

Text #5

Max Range: 0.1461. Min Range: -0.1461

Max Act: 0.1063. Min Act: -0.0000

Data Index: 775622 (C4 (Web Text))

Max Activating Token Index: 660

Text #6

Max Range: 0.1461. Min Range: -0.1461

Max Act: 0.1091. Min Act: -0.0000

Data Index: 690522 (C4 (Web Text))

Max Activating Token Index: 366

Text #7

Max Range: 0.1461. Min Range: -0.1461

Max Act: 0.1077. Min Act: -0.0000

Data Index: 93438 (C4 (Web Text))

Max Activating Token Index: 912

Text #8

Max Range: 0.1461. Min Range: -0.1461

Max Act: 0.1063. Min Act: -0.0000

Data Index: 1149147 (C4 (Web Text))

Max Activating Token Index: 242

Text #9

Max Range: 0.1461. Min Range: -0.1461

Max Act: 0.1043. Min Act: -0.0000

Data Index: 439137 (C4 (Web Text))

Max Activating Token Index: 1002

Text #10

Max Range: 0.1461. Min Range: -0.1461

Max Act: 0.1045. Min Act: -0.0000

Data Index: 433742 (C4 (Web Text))

Max Activating Token Index: 701

Text #11

Max Range: 0.1461. Min Range: -0.1461

Max Act: 0.1018. Min Act: -0.0000

Data Index: 827493 (C4 (Web Text))

Max Activating Token Index: 101

Text #12

Max Range: 0.1461. Min Range: -0.1461

Max Act: 0.0989. Min Act: -0.0001

Data Index: 875195 (C4 (Web Text))

Max Activating Token Index: 564

Text #13

Max Range: 0.1461. Min Range: -0.1461

Max Act: 0.0978. Min Act: -0.0000

Data Index: 139068 (C4 (Web Text))

Max Activating Token Index: 452

Text #14

Max Range: 0.1461. Min Range: -0.1461

Max Act: 0.0965. Min Act: -0.0000

Data Index: 147193 (C4 (Web Text))

Max Activating Token Index: 720

Text #15

Max Range: 0.1461. Min Range: -0.1461

Max Act: 0.0952. Min Act: -0.0000

Data Index: 1325881 (C4 (Web Text))

Max Activating Token Index: 955

Text #16

Max Range: 0.1461. Min Range: -0.1461

Max Act: 0.0906. Min Act: -0.0000

Data Index: 63520 (C4 (Web Text))

Max Activating Token Index: 125

Text #17

Max Range: 0.1461. Min Range: -0.1461

Max Act: 0.0927. Min Act: -0.0001

Data Index: 744523 (C4 (Web Text))

Max Activating Token Index: 150

Text #18

Max Range: 0.1461. Min Range: -0.1461

Max Act: 0.0912. Min Act: -0.0001

Data Index: 21241 (C4 (Web Text))

Max Activating Token Index: 637

Text #19

Max Range: 0.1461. Min Range: -0.1461

Max Act: 0.0872. Min Act: -0.0000

Data Index: 656498 (C4 (Web Text))

Max Activating Token Index: 584