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

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

Neuron 1064 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.7911. Min Range: -4.7911

Max Act: 4.7911. Min Act: -0.0000

Data Index: 541183 (C4 (Web Text))

Max Activating Token Index: 913

Text #1

Max Range: 4.7911. Min Range: -4.7911

Max Act: 4.6447. Min Act: -0.0000

Data Index: 1002986 (C4 (Web Text))

Max Activating Token Index: 928

Text #2

Max Range: 4.7911. Min Range: -4.7911

Max Act: 4.5890. Min Act: -0.0000

Data Index: 783954 (C4 (Web Text))

Max Activating Token Index: 633

Text #3

Max Range: 4.7911. Min Range: -4.7911

Max Act: 4.1219. Min Act: -0.0000

Data Index: 822039 (C4 (Web Text))

Max Activating Token Index: 771

Text #4

Max Range: 4.7911. Min Range: -4.7911

Max Act: 4.2925. Min Act: -0.0000

Data Index: 526205 (C4 (Web Text))

Max Activating Token Index: 13

Text #5

Max Range: 4.7911. Min Range: -4.7911

Max Act: 4.0560. Min Act: -0.0000

Data Index: 1356160 (C4 (Web Text))

Max Activating Token Index: 90

Text #6

Max Range: 4.7911. Min Range: -4.7911

Max Act: 3.9086. Min Act: -0.0000

Data Index: 627444 (C4 (Web Text))

Max Activating Token Index: 477

Text #7

Max Range: 4.7911. Min Range: -4.7911

Max Act: 4.0343. Min Act: -0.0000

Data Index: 910685 (C4 (Web Text))

Max Activating Token Index: 107

Text #8

Max Range: 4.7911. Min Range: -4.7911

Max Act: 4.3092. Min Act: -0.0000

Data Index: 992493 (C4 (Web Text))

Max Activating Token Index: 29

Text #9

Max Range: 4.7911. Min Range: -4.7911

Max Act: 3.7474. Min Act: -0.0000

Data Index: 1125587 (C4 (Web Text))

Max Activating Token Index: 541

Text #10

Max Range: 4.7911. Min Range: -4.7911

Max Act: 3.7238. Min Act: -0.0000

Data Index: 161544 (C4 (Web Text))

Max Activating Token Index: 141

Text #11

Max Range: 4.7911. Min Range: -4.7911

Max Act: 3.8326. Min Act: -0.0000

Data Index: 751867 (C4 (Web Text))

Max Activating Token Index: 692

Text #12

Max Range: 4.7911. Min Range: -4.7911

Max Act: 3.6452. Min Act: -0.0000

Data Index: 997844 (C4 (Web Text))

Max Activating Token Index: 915

Text #13

Max Range: 4.7911. Min Range: -4.7911

Max Act: 3.9251. Min Act: -0.0000

Data Index: 6048 (C4 (Web Text))

Max Activating Token Index: 914

Text #14

Max Range: 4.7911. Min Range: -4.7911

Max Act: 3.5670. Min Act: -0.0000

Data Index: 408434 (C4 (Web Text))

Max Activating Token Index: 311

Text #15

Max Range: 4.7911. Min Range: -4.7911

Max Act: 3.7648. Min Act: -0.0000

Data Index: 118742 (C4 (Web Text))

Max Activating Token Index: 356

Text #16

Max Range: 4.7911. Min Range: -4.7911

Max Act: 3.8639. Min Act: -0.0000

Data Index: 1199350 (C4 (Web Text))

Max Activating Token Index: 229

Text #17

Max Range: 4.7911. Min Range: -4.7911

Max Act: 3.5445. Min Act: -0.0000

Data Index: 333766 (C4 (Web Text))

Max Activating Token Index: 451

Text #18

Max Range: 4.7911. Min Range: -4.7911

Max Act: 3.5101. Min Act: -0.0000

Data Index: 66034 (C4 (Web Text))

Max Activating Token Index: 916

Text #19

Max Range: 4.7911. Min Range: -4.7911

Max Act: 3.9809. Min Act: -0.0000

Data Index: 1338462 (C4 (Web Text))

Max Activating Token Index: 966