Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5584 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.4796. Min Range: -0.4796

Max Act: 0.4796. Min Act: -0.0000

Data Index: 170988 (C4 (Web Text))

Max Activating Token Index: 397

Text #1

Max Range: 0.4796. Min Range: -0.4796

Max Act: 0.4080. Min Act: -0.0000

Data Index: 251038 (C4 (Web Text))

Max Activating Token Index: 747

Text #2

Max Range: 0.4796. Min Range: -0.4796

Max Act: 0.3413. Min Act: -0.0000

Data Index: 1556855 (Python Code)

Max Activating Token Index: 258

Text #3

Max Range: 0.4796. Min Range: -0.4796

Max Act: 0.3235. Min Act: -0.0000

Data Index: 1106988 (C4 (Web Text))

Max Activating Token Index: 460

Text #4

Max Range: 0.4796. Min Range: -0.4796

Max Act: 0.3411. Min Act: -0.0000

Data Index: 276317 (C4 (Web Text))

Max Activating Token Index: 662

Text #5

Max Range: 0.4796. Min Range: -0.4796

Max Act: 0.3188. Min Act: -0.0000

Data Index: 1002220 (C4 (Web Text))

Max Activating Token Index: 887

Text #6

Max Range: 0.4796. Min Range: -0.4796

Max Act: 0.3218. Min Act: -0.0000

Data Index: 1252047 (C4 (Web Text))

Max Activating Token Index: 510

Text #7

Max Range: 0.4796. Min Range: -0.4796

Max Act: 0.3074. Min Act: -0.0000

Data Index: 442712 (C4 (Web Text))

Max Activating Token Index: 362

Text #8

Max Range: 0.4796. Min Range: -0.4796

Max Act: 0.3030. Min Act: -0.0000

Data Index: 788257 (C4 (Web Text))

Max Activating Token Index: 965

Text #9

Max Range: 0.4796. Min Range: -0.4796

Max Act: 0.3100. Min Act: -0.0000

Data Index: 883612 (C4 (Web Text))

Max Activating Token Index: 918

Text #10

Max Range: 0.4796. Min Range: -0.4796

Max Act: 0.3288. Min Act: -0.0000

Data Index: 954506 (C4 (Web Text))

Max Activating Token Index: 822

Text #11

Max Range: 0.4796. Min Range: -0.4796

Max Act: 0.3057. Min Act: -0.0000

Data Index: 1545692 (Python Code)

Max Activating Token Index: 337

Text #12

Max Range: 0.4796. Min Range: -0.4796

Max Act: 0.3178. Min Act: -0.0000

Data Index: 1478818 (Python Code)

Max Activating Token Index: 268

Text #13

Max Range: 0.4796. Min Range: -0.4796

Max Act: 0.3038. Min Act: -0.0000

Data Index: 1203944 (C4 (Web Text))

Max Activating Token Index: 418

Text #14

Max Range: 0.4796. Min Range: -0.4796

Max Act: 0.3008. Min Act: -0.0000

Data Index: 1507916 (Python Code)

Max Activating Token Index: 756

Text #15

Max Range: 0.4796. Min Range: -0.4796

Max Act: 0.3095. Min Act: -0.0000

Data Index: 804661 (C4 (Web Text))

Max Activating Token Index: 976

Text #16

Max Range: 0.4796. Min Range: -0.4796

Max Act: 0.2807. Min Act: -0.0000

Data Index: 139027 (C4 (Web Text))

Max Activating Token Index: 777

Text #17

Max Range: 0.4796. Min Range: -0.4796

Max Act: 0.2850. Min Act: -0.0000

Data Index: 303731 (C4 (Web Text))

Max Activating Token Index: 416

Text #18

Max Range: 0.4796. Min Range: -0.4796

Max Act: 0.2809. Min Act: -0.0000

Data Index: 1331203 (C4 (Web Text))

Max Activating Token Index: 122

Text #19

Max Range: 0.4796. Min Range: -0.4796

Max Act: 0.2876. Min Act: -0.0000

Data Index: 1588201 (Python Code)

Max Activating Token Index: 172