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

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

Neuron 3584 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.3948. Min Range: -5.3948

Max Act: 5.3948. Min Act: -0.0000

Data Index: 1153894 (C4 (Web Text))

Max Activating Token Index: 464

Text #1

Max Range: 5.3948. Min Range: -5.3948

Max Act: 4.0213. Min Act: -0.0000

Data Index: 1024027 (C4 (Web Text))

Max Activating Token Index: 356

Text #2

Max Range: 5.3948. Min Range: -5.3948

Max Act: 3.4985. Min Act: -0.0000

Data Index: 202758 (C4 (Web Text))

Max Activating Token Index: 176

Text #3

Max Range: 5.3948. Min Range: -5.3948

Max Act: 3.3956. Min Act: -0.0000

Data Index: 1049635 (C4 (Web Text))

Max Activating Token Index: 1015

Text #4

Max Range: 5.3948. Min Range: -5.3948

Max Act: 2.8622. Min Act: -0.0000

Data Index: 573633 (C4 (Web Text))

Max Activating Token Index: 866

Text #5

Max Range: 5.3948. Min Range: -5.3948

Max Act: 3.1246. Min Act: -0.0000

Data Index: 786652 (C4 (Web Text))

Max Activating Token Index: 455

Text #6

Max Range: 5.3948. Min Range: -5.3948

Max Act: 2.3586. Min Act: -0.0000

Data Index: 400954 (C4 (Web Text))

Max Activating Token Index: 984

Text #7

Max Range: 5.3948. Min Range: -5.3948

Max Act: 2.6806. Min Act: -0.0000

Data Index: 554679 (C4 (Web Text))

Max Activating Token Index: 307

Text #8

Max Range: 5.3948. Min Range: -5.3948

Max Act: 2.7597. Min Act: -0.0000

Data Index: 785376 (C4 (Web Text))

Max Activating Token Index: 765

Text #9

Max Range: 5.3948. Min Range: -5.3948

Max Act: 2.7313. Min Act: -0.0000

Data Index: 870934 (C4 (Web Text))

Max Activating Token Index: 859

Text #10

Max Range: 5.3948. Min Range: -5.3948

Max Act: 2.5865. Min Act: -0.0000

Data Index: 738187 (C4 (Web Text))

Max Activating Token Index: 959

Text #11

Max Range: 5.3948. Min Range: -5.3948

Max Act: 2.9802. Min Act: -0.0000

Data Index: 117304 (C4 (Web Text))

Max Activating Token Index: 34

Text #12

Max Range: 5.3948. Min Range: -5.3948

Max Act: 2.6211. Min Act: -0.0000

Data Index: 874091 (C4 (Web Text))

Max Activating Token Index: 593

Text #13

Max Range: 5.3948. Min Range: -5.3948

Max Act: 2.3702. Min Act: -0.0000

Data Index: 654315 (C4 (Web Text))

Max Activating Token Index: 753

Text #14

Max Range: 5.3948. Min Range: -5.3948

Max Act: 2.0989. Min Act: -0.0000

Data Index: 270569 (C4 (Web Text))

Max Activating Token Index: 904

Text #15

Max Range: 5.3948. Min Range: -5.3948

Max Act: 2.3529. Min Act: -0.0000

Data Index: 365249 (C4 (Web Text))

Max Activating Token Index: 866

Text #16

Max Range: 5.3948. Min Range: -5.3948

Max Act: 2.4710. Min Act: -0.0000

Data Index: 1260027 (C4 (Web Text))

Max Activating Token Index: 889

Text #17

Max Range: 5.3948. Min Range: -5.3948

Max Act: 2.4934. Min Act: -0.0000

Data Index: 1231641 (C4 (Web Text))

Max Activating Token Index: 133

Text #18

Max Range: 5.3948. Min Range: -5.3948

Max Act: 2.2061. Min Act: -0.0000

Data Index: 1219354 (C4 (Web Text))

Max Activating Token Index: 642

Text #19

Max Range: 5.3948. Min Range: -5.3948

Max Act: 2.3359. Min Act: -0.0000

Data Index: 604458 (C4 (Web Text))

Max Activating Token Index: 544