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

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

Neuron 1577 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4397. Min Range: -1.4397

Max Act: 1.3945. Min Act: -0.0002

Data Index: 63973 (C4 (Web Text))

Max Activating Token Index: 638

Text #1

Max Range: 1.4397. Min Range: -1.4397

Max Act: 1.4397. Min Act: -0.0002

Data Index: 928466 (C4 (Web Text))

Max Activating Token Index: 809

Text #2

Max Range: 1.4397. Min Range: -1.4397

Max Act: 1.3391. Min Act: -0.0002

Data Index: 612789 (C4 (Web Text))

Max Activating Token Index: 514

Text #3

Max Range: 1.4397. Min Range: -1.4397

Max Act: 1.4035. Min Act: -0.0002

Data Index: 1327932 (C4 (Web Text))

Max Activating Token Index: 793

Text #4

Max Range: 1.4397. Min Range: -1.4397

Max Act: 1.2176. Min Act: -0.0001

Data Index: 823348 (C4 (Web Text))

Max Activating Token Index: 137

Text #5

Max Range: 1.4397. Min Range: -1.4397

Max Act: 1.2975. Min Act: -0.0002

Data Index: 571101 (C4 (Web Text))

Max Activating Token Index: 46

Text #6

Max Range: 1.4397. Min Range: -1.4397

Max Act: 1.2251. Min Act: -0.0001

Data Index: 177786 (C4 (Web Text))

Max Activating Token Index: 647

Text #7

Max Range: 1.4397. Min Range: -1.4397

Max Act: 1.2468. Min Act: -0.0002

Data Index: 270550 (C4 (Web Text))

Max Activating Token Index: 172

Text #8

Max Range: 1.4397. Min Range: -1.4397

Max Act: 1.2080. Min Act: -0.0002

Data Index: 85203 (C4 (Web Text))

Max Activating Token Index: 715

Text #9

Max Range: 1.4397. Min Range: -1.4397

Max Act: 1.2295. Min Act: -0.0001

Data Index: 1357588 (C4 (Web Text))

Max Activating Token Index: 29

Text #10

Max Range: 1.4397. Min Range: -1.4397

Max Act: 1.2140. Min Act: -0.0002

Data Index: 820957 (C4 (Web Text))

Max Activating Token Index: 172

Text #11

Max Range: 1.4397. Min Range: -1.4397

Max Act: 1.1785. Min Act: -0.0002

Data Index: 323129 (C4 (Web Text))

Max Activating Token Index: 881

Text #12

Max Range: 1.4397. Min Range: -1.4397

Max Act: 1.1007. Min Act: -0.0002

Data Index: 1003123 (C4 (Web Text))

Max Activating Token Index: 280

Text #13

Max Range: 1.4397. Min Range: -1.4397

Max Act: 1.1632. Min Act: -0.0001

Data Index: 1055845 (C4 (Web Text))

Max Activating Token Index: 918

Text #14

Max Range: 1.4397. Min Range: -1.4397

Max Act: 1.1868. Min Act: -0.0001

Data Index: 1268 (C4 (Web Text))

Max Activating Token Index: 131

Text #15

Max Range: 1.4397. Min Range: -1.4397

Max Act: 1.1487. Min Act: -0.0002

Data Index: 800527 (C4 (Web Text))

Max Activating Token Index: 912

Text #16

Max Range: 1.4397. Min Range: -1.4397

Max Act: 1.1173. Min Act: -0.0001

Data Index: 987326 (C4 (Web Text))

Max Activating Token Index: 901

Text #17

Max Range: 1.4397. Min Range: -1.4397

Max Act: 1.1719. Min Act: -0.0002

Data Index: 836479 (C4 (Web Text))

Max Activating Token Index: 243

Text #18

Max Range: 1.4397. Min Range: -1.4397

Max Act: 1.1698. Min Act: -0.0001

Data Index: 1065942 (C4 (Web Text))

Max Activating Token Index: 72

Text #19

Max Range: 1.4397. Min Range: -1.4397

Max Act: 1.3092. Min Act: -0.0002

Data Index: 1160079 (C4 (Web Text))

Max Activating Token Index: 808