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

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

Neuron 808 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7943. Min Range: -0.7943

Max Act: 0.7943. Min Act: -0.0000

Data Index: 1316803 (C4 (Web Text))

Max Activating Token Index: 814

Text #1

Max Range: 0.7943. Min Range: -0.7943

Max Act: 0.6459. Min Act: -0.0001

Data Index: 700769 (C4 (Web Text))

Max Activating Token Index: 1007

Text #2

Max Range: 0.7943. Min Range: -0.7943

Max Act: 0.7152. Min Act: -0.0001

Data Index: 369919 (C4 (Web Text))

Max Activating Token Index: 641

Text #3

Max Range: 0.7943. Min Range: -0.7943

Max Act: 0.6572. Min Act: -0.0001

Data Index: 1287706 (C4 (Web Text))

Max Activating Token Index: 544

Text #4

Max Range: 0.7943. Min Range: -0.7943

Max Act: 0.6359. Min Act: -0.0001

Data Index: 1329032 (C4 (Web Text))

Max Activating Token Index: 40

Text #5

Max Range: 0.7943. Min Range: -0.7943

Max Act: 0.6536. Min Act: -0.0001

Data Index: 453751 (C4 (Web Text))

Max Activating Token Index: 706

Text #6

Max Range: 0.7943. Min Range: -0.7943

Max Act: 0.6096. Min Act: -0.0001

Data Index: 179605 (C4 (Web Text))

Max Activating Token Index: 263

Text #7

Max Range: 0.7943. Min Range: -0.7943

Max Act: 0.6085. Min Act: -0.0001

Data Index: 1015003 (C4 (Web Text))

Max Activating Token Index: 746

Text #8

Max Range: 0.7943. Min Range: -0.7943

Max Act: 0.6585. Min Act: -0.0001

Data Index: 356328 (C4 (Web Text))

Max Activating Token Index: 97

Text #9

Max Range: 0.7943. Min Range: -0.7943

Max Act: 0.5440. Min Act: -0.0001

Data Index: 1145393 (C4 (Web Text))

Max Activating Token Index: 144

Text #10

Max Range: 0.7943. Min Range: -0.7943

Max Act: 0.6331. Min Act: -0.0001

Data Index: 104330 (C4 (Web Text))

Max Activating Token Index: 750

Text #11

Max Range: 0.7943. Min Range: -0.7943

Max Act: 0.4899. Min Act: -0.0001

Data Index: 709349 (C4 (Web Text))

Max Activating Token Index: 211

Text #12

Max Range: 0.7943. Min Range: -0.7943

Max Act: 0.5448. Min Act: -0.0001

Data Index: 123022 (C4 (Web Text))

Max Activating Token Index: 39

Text #13

Max Range: 0.7943. Min Range: -0.7943

Max Act: 0.5244. Min Act: -0.0001

Data Index: 644568 (C4 (Web Text))

Max Activating Token Index: 93

Text #14

Max Range: 0.7943. Min Range: -0.7943

Max Act: 0.5844. Min Act: -0.0001

Data Index: 700926 (C4 (Web Text))

Max Activating Token Index: 383

Text #15

Max Range: 0.7943. Min Range: -0.7943

Max Act: 0.5325. Min Act: -0.0000

Data Index: 235197 (C4 (Web Text))

Max Activating Token Index: 1008

Text #16

Max Range: 0.7943. Min Range: -0.7943

Max Act: 0.4771. Min Act: -0.0001

Data Index: 879024 (C4 (Web Text))

Max Activating Token Index: 630

Text #17

Max Range: 0.7943. Min Range: -0.7943

Max Act: 0.5413. Min Act: -0.0001

Data Index: 1313073 (C4 (Web Text))

Max Activating Token Index: 391

Text #18

Max Range: 0.7943. Min Range: -0.7943

Max Act: 0.5248. Min Act: -0.0000

Data Index: 475375 (C4 (Web Text))

Max Activating Token Index: 69

Text #19

Max Range: 0.7943. Min Range: -0.7943

Max Act: 0.4628. Min Act: -0.0001

Data Index: 406310 (C4 (Web Text))

Max Activating Token Index: 274