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

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

Neuron 3850 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3057. Min Range: -0.3057

Max Act: 0.2661. Min Act: -0.0000

Data Index: 862699 (C4 (Web Text))

Max Activating Token Index: 285

Text #1

Max Range: 0.3057. Min Range: -0.3057

Max Act: 0.2834. Min Act: -0.0000

Data Index: 1281101 (C4 (Web Text))

Max Activating Token Index: 84

Text #2

Max Range: 0.3057. Min Range: -0.3057

Max Act: 0.2895. Min Act: -0.0000

Data Index: 1063982 (C4 (Web Text))

Max Activating Token Index: 123

Text #3

Max Range: 0.3057. Min Range: -0.3057

Max Act: 0.2834. Min Act: -0.0000

Data Index: 310331 (C4 (Web Text))

Max Activating Token Index: 197

Text #4

Max Range: 0.3057. Min Range: -0.3057

Max Act: 0.2930. Min Act: -0.0000

Data Index: 685688 (C4 (Web Text))

Max Activating Token Index: 123

Text #5

Max Range: 0.3057. Min Range: -0.3057

Max Act: 0.2769. Min Act: -0.0000

Data Index: 749620 (C4 (Web Text))

Max Activating Token Index: 918

Text #6

Max Range: 0.3057. Min Range: -0.3057

Max Act: 0.2725. Min Act: -0.0000

Data Index: 216811 (C4 (Web Text))

Max Activating Token Index: 992

Text #7

Max Range: 0.3057. Min Range: -0.3057

Max Act: 0.2641. Min Act: -0.0000

Data Index: 1283617 (C4 (Web Text))

Max Activating Token Index: 1007

Text #8

Max Range: 0.3057. Min Range: -0.3057

Max Act: 0.3057. Min Act: -0.0000

Data Index: 267503 (C4 (Web Text))

Max Activating Token Index: 829

Text #9

Max Range: 0.3057. Min Range: -0.3057

Max Act: 0.2547. Min Act: -0.0000

Data Index: 377326 (C4 (Web Text))

Max Activating Token Index: 349

Text #10

Max Range: 0.3057. Min Range: -0.3057

Max Act: 0.2700. Min Act: -0.0000

Data Index: 914329 (C4 (Web Text))

Max Activating Token Index: 320

Text #11

Max Range: 0.3057. Min Range: -0.3057

Max Act: 0.2478. Min Act: -0.0000

Data Index: 160427 (C4 (Web Text))

Max Activating Token Index: 81

Text #12

Max Range: 0.3057. Min Range: -0.3057

Max Act: 0.2515. Min Act: -0.0000

Data Index: 782749 (C4 (Web Text))

Max Activating Token Index: 456

Text #13

Max Range: 0.3057. Min Range: -0.3057

Max Act: 0.2672. Min Act: -0.0000

Data Index: 462055 (C4 (Web Text))

Max Activating Token Index: 904

Text #14

Max Range: 0.3057. Min Range: -0.3057

Max Act: 0.2640. Min Act: -0.0000

Data Index: 625271 (C4 (Web Text))

Max Activating Token Index: 1020

Text #15

Max Range: 0.3057. Min Range: -0.3057

Max Act: 0.2320. Min Act: -0.0000

Data Index: 423262 (C4 (Web Text))

Max Activating Token Index: 729

Text #16

Max Range: 0.3057. Min Range: -0.3057

Max Act: 0.2509. Min Act: -0.0000

Data Index: 1181338 (C4 (Web Text))

Max Activating Token Index: 520

Text #17

Max Range: 0.3057. Min Range: -0.3057

Max Act: 0.2373. Min Act: -0.0000

Data Index: 546337 (C4 (Web Text))

Max Activating Token Index: 204

Text #18

Max Range: 0.3057. Min Range: -0.3057

Max Act: 0.2148. Min Act: -0.0000

Data Index: 508260 (C4 (Web Text))

Max Activating Token Index: 621

Text #19

Max Range: 0.3057. Min Range: -0.3057

Max Act: 0.2252. Min Act: -0.0000

Data Index: 1088661 (C4 (Web Text))

Max Activating Token Index: 29