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

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

Neuron 1010 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1334. Min Range: -0.1334

Max Act: 0.1334. Min Act: -0.0001

Data Index: 594263 (C4 (Web Text))

Max Activating Token Index: 958

Text #1

Max Range: 0.1334. Min Range: -0.1334

Max Act: 0.1317. Min Act: -0.0001

Data Index: 355263 (C4 (Web Text))

Max Activating Token Index: 170

Text #2

Max Range: 0.1334. Min Range: -0.1334

Max Act: 0.1333. Min Act: -0.0001

Data Index: 464918 (C4 (Web Text))

Max Activating Token Index: 104

Text #3

Max Range: 0.1334. Min Range: -0.1334

Max Act: 0.1322. Min Act: -0.0001

Data Index: 847015 (C4 (Web Text))

Max Activating Token Index: 89

Text #4

Max Range: 0.1334. Min Range: -0.1334

Max Act: 0.1285. Min Act: -0.0001

Data Index: 1355489 (C4 (Web Text))

Max Activating Token Index: 505

Text #5

Max Range: 0.1334. Min Range: -0.1334

Max Act: 0.1040. Min Act: -0.0001

Data Index: 1305220 (C4 (Web Text))

Max Activating Token Index: 330

Text #6

Max Range: 0.1334. Min Range: -0.1334

Max Act: 0.1079. Min Act: -0.0001

Data Index: 1320323 (C4 (Web Text))

Max Activating Token Index: 10

Text #7

Max Range: 0.1334. Min Range: -0.1334

Max Act: 0.1003. Min Act: -0.0001

Data Index: 708939 (C4 (Web Text))

Max Activating Token Index: 644

Text #8

Max Range: 0.1334. Min Range: -0.1334

Max Act: 0.1035. Min Act: -0.0001

Data Index: 267307 (C4 (Web Text))

Max Activating Token Index: 672

Text #9

Max Range: 0.1334. Min Range: -0.1334

Max Act: 0.0952. Min Act: -0.0001

Data Index: 1255531 (C4 (Web Text))

Max Activating Token Index: 631

Text #10

Max Range: 0.1334. Min Range: -0.1334

Max Act: 0.1066. Min Act: -0.0001

Data Index: 369807 (C4 (Web Text))

Max Activating Token Index: 83

Text #11

Max Range: 0.1334. Min Range: -0.1334

Max Act: 0.0974. Min Act: -0.0001

Data Index: 1229607 (C4 (Web Text))

Max Activating Token Index: 932

Text #12

Max Range: 0.1334. Min Range: -0.1334

Max Act: 0.0993. Min Act: -0.0001

Data Index: 1129207 (C4 (Web Text))

Max Activating Token Index: 900

Text #13

Max Range: 0.1334. Min Range: -0.1334

Max Act: 0.0927. Min Act: -0.0001

Data Index: 81760 (C4 (Web Text))

Max Activating Token Index: 968

Text #14

Max Range: 0.1334. Min Range: -0.1334

Max Act: 0.0990. Min Act: -0.0001

Data Index: 652184 (C4 (Web Text))

Max Activating Token Index: 322

Text #15

Max Range: 0.1334. Min Range: -0.1334

Max Act: 0.1003. Min Act: -0.0001

Data Index: 1324720 (C4 (Web Text))

Max Activating Token Index: 994

Text #16

Max Range: 0.1334. Min Range: -0.1334

Max Act: 0.0988. Min Act: -0.0001

Data Index: 718147 (C4 (Web Text))

Max Activating Token Index: 431

Text #17

Max Range: 0.1334. Min Range: -0.1334

Max Act: 0.0854. Min Act: -0.0001

Data Index: 1151114 (C4 (Web Text))

Max Activating Token Index: 746

Text #18

Max Range: 0.1334. Min Range: -0.1334

Max Act: 0.0930. Min Act: -0.0001

Data Index: 116733 (C4 (Web Text))

Max Activating Token Index: 85

Text #19

Max Range: 0.1334. Min Range: -0.1334

Max Act: 0.0974. Min Act: -0.0001

Data Index: 691939 (C4 (Web Text))

Max Activating Token Index: 165