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

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

Neuron 4368 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: 3.0968. Min Range: -3.0968

Max Act: 3.0117. Min Act: -0.0000

Data Index: 500842 (C4 (Web Text))

Max Activating Token Index: 424

Text #1

Max Range: 3.0968. Min Range: -3.0968

Max Act: 3.0968. Min Act: -0.0000

Data Index: 204003 (C4 (Web Text))

Max Activating Token Index: 940

Text #2

Max Range: 3.0968. Min Range: -3.0968

Max Act: 2.6592. Min Act: -0.0000

Data Index: 361187 (C4 (Web Text))

Max Activating Token Index: 272

Text #3

Max Range: 3.0968. Min Range: -3.0968

Max Act: 2.4717. Min Act: -0.0000

Data Index: 12174 (C4 (Web Text))

Max Activating Token Index: 203

Text #4

Max Range: 3.0968. Min Range: -3.0968

Max Act: 2.6861. Min Act: -0.0000

Data Index: 304735 (C4 (Web Text))

Max Activating Token Index: 19

Text #5

Max Range: 3.0968. Min Range: -3.0968

Max Act: 2.4464. Min Act: -0.0000

Data Index: 1037116 (C4 (Web Text))

Max Activating Token Index: 922

Text #6

Max Range: 3.0968. Min Range: -3.0968

Max Act: 2.4250. Min Act: -0.0000

Data Index: 992659 (C4 (Web Text))

Max Activating Token Index: 292

Text #7

Max Range: 3.0968. Min Range: -3.0968

Max Act: 2.4660. Min Act: -0.0000

Data Index: 478016 (C4 (Web Text))

Max Activating Token Index: 18

Text #8

Max Range: 3.0968. Min Range: -3.0968

Max Act: 2.3766. Min Act: -0.0000

Data Index: 1288798 (C4 (Web Text))

Max Activating Token Index: 552

Text #9

Max Range: 3.0968. Min Range: -3.0968

Max Act: 2.2178. Min Act: -0.0000

Data Index: 329908 (C4 (Web Text))

Max Activating Token Index: 802

Text #10

Max Range: 3.0968. Min Range: -3.0968

Max Act: 2.2247. Min Act: -0.0000

Data Index: 870863 (C4 (Web Text))

Max Activating Token Index: 24

Text #11

Max Range: 3.0968. Min Range: -3.0968

Max Act: 2.3446. Min Act: -0.0000

Data Index: 694760 (C4 (Web Text))

Max Activating Token Index: 561

Text #12

Max Range: 3.0968. Min Range: -3.0968

Max Act: 2.3248. Min Act: -0.0000

Data Index: 925325 (C4 (Web Text))

Max Activating Token Index: 815

Text #13

Max Range: 3.0968. Min Range: -3.0968

Max Act: 1.9897. Min Act: -0.0000

Data Index: 1071204 (C4 (Web Text))

Max Activating Token Index: 919

Text #14

Max Range: 3.0968. Min Range: -3.0968

Max Act: 2.2563. Min Act: -0.0000

Data Index: 1134922 (C4 (Web Text))

Max Activating Token Index: 714

Text #15

Max Range: 3.0968. Min Range: -3.0968

Max Act: 2.4938. Min Act: -0.0000

Data Index: 398721 (C4 (Web Text))

Max Activating Token Index: 943

Text #16

Max Range: 3.0968. Min Range: -3.0968

Max Act: 2.2435. Min Act: -0.0000

Data Index: 899397 (C4 (Web Text))

Max Activating Token Index: 901

Text #17

Max Range: 3.0968. Min Range: -3.0968

Max Act: 2.0965. Min Act: -0.0000

Data Index: 1322548 (C4 (Web Text))

Max Activating Token Index: 476

Text #18

Max Range: 3.0968. Min Range: -3.0968

Max Act: 2.0975. Min Act: -0.0000

Data Index: 697129 (C4 (Web Text))

Max Activating Token Index: 227

Text #19

Max Range: 3.0968. Min Range: -3.0968

Max Act: 2.0775. Min Act: -0.0000

Data Index: 962949 (C4 (Web Text))

Max Activating Token Index: 521