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

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

Neuron 4932 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2679. Min Range: -2.2679

Max Act: 2.2679. Min Act: -0.0000

Data Index: 1035620 (C4 (Web Text))

Max Activating Token Index: 83

Text #1

Max Range: 2.2679. Min Range: -2.2679

Max Act: 1.9274. Min Act: -0.0000

Data Index: 1073250 (C4 (Web Text))

Max Activating Token Index: 1020

Text #2

Max Range: 2.2679. Min Range: -2.2679

Max Act: 1.9210. Min Act: -0.0000

Data Index: 553645 (C4 (Web Text))

Max Activating Token Index: 102

Text #3

Max Range: 2.2679. Min Range: -2.2679

Max Act: 1.8404. Min Act: -0.0000

Data Index: 985915 (C4 (Web Text))

Max Activating Token Index: 39

Text #4

Max Range: 2.2679. Min Range: -2.2679

Max Act: 1.8866. Min Act: -0.0000

Data Index: 184119 (C4 (Web Text))

Max Activating Token Index: 370

Text #5

Max Range: 2.2679. Min Range: -2.2679

Max Act: 1.6694. Min Act: -0.0000

Data Index: 312976 (C4 (Web Text))

Max Activating Token Index: 120

Text #6

Max Range: 2.2679. Min Range: -2.2679

Max Act: 1.7722. Min Act: -0.0000

Data Index: 299624 (C4 (Web Text))

Max Activating Token Index: 91

Text #7

Max Range: 2.2679. Min Range: -2.2679

Max Act: 1.7448. Min Act: -0.0000

Data Index: 974972 (C4 (Web Text))

Max Activating Token Index: 132

Text #8

Max Range: 2.2679. Min Range: -2.2679

Max Act: 1.6961. Min Act: -0.0000

Data Index: 1339430 (C4 (Web Text))

Max Activating Token Index: 51

Text #9

Max Range: 2.2679. Min Range: -2.2679

Max Act: 1.6591. Min Act: -0.0000

Data Index: 513770 (C4 (Web Text))

Max Activating Token Index: 200

Text #10

Max Range: 2.2679. Min Range: -2.2679

Max Act: 1.6531. Min Act: -0.0000

Data Index: 417827 (C4 (Web Text))

Max Activating Token Index: 289

Text #11

Max Range: 2.2679. Min Range: -2.2679

Max Act: 1.6372. Min Act: -0.0000

Data Index: 8328 (C4 (Web Text))

Max Activating Token Index: 354

Text #12

Max Range: 2.2679. Min Range: -2.2679

Max Act: 1.6452. Min Act: -0.0000

Data Index: 315414 (C4 (Web Text))

Max Activating Token Index: 64

Text #13

Max Range: 2.2679. Min Range: -2.2679

Max Act: 1.7225. Min Act: -0.0000

Data Index: 832044 (C4 (Web Text))

Max Activating Token Index: 1022

Text #14

Max Range: 2.2679. Min Range: -2.2679

Max Act: 1.6164. Min Act: -0.0000

Data Index: 1068852 (C4 (Web Text))

Max Activating Token Index: 495

Text #15

Max Range: 2.2679. Min Range: -2.2679

Max Act: 1.6251. Min Act: -0.0000

Data Index: 130862 (C4 (Web Text))

Max Activating Token Index: 472

Text #16

Max Range: 2.2679. Min Range: -2.2679

Max Act: 1.6153. Min Act: -0.0000

Data Index: 145575 (C4 (Web Text))

Max Activating Token Index: 119

Text #17

Max Range: 2.2679. Min Range: -2.2679

Max Act: 1.5885. Min Act: -0.0000

Data Index: 1060987 (C4 (Web Text))

Max Activating Token Index: 911

Text #18

Max Range: 2.2679. Min Range: -2.2679

Max Act: 1.5356. Min Act: -0.0000

Data Index: 1276389 (C4 (Web Text))

Max Activating Token Index: 247

Text #19

Max Range: 2.2679. Min Range: -2.2679

Max Act: 1.5318. Min Act: -0.0000

Data Index: 2609 (C4 (Web Text))

Max Activating Token Index: 129