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

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

Neuron 2102 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: 0.9768. Min Range: -0.9768

Max Act: 0.9768. Min Act: -0.0000

Data Index: 929647 (C4 (Web Text))

Max Activating Token Index: 235

Text #1

Max Range: 0.9768. Min Range: -0.9768

Max Act: 0.8743. Min Act: -0.0000

Data Index: 70016 (C4 (Web Text))

Max Activating Token Index: 584

Text #2

Max Range: 0.9768. Min Range: -0.9768

Max Act: 0.9028. Min Act: -0.0000

Data Index: 1260364 (C4 (Web Text))

Max Activating Token Index: 91

Text #3

Max Range: 0.9768. Min Range: -0.9768

Max Act: 0.8810. Min Act: -0.0000

Data Index: 1110320 (C4 (Web Text))

Max Activating Token Index: 853

Text #4

Max Range: 0.9768. Min Range: -0.9768

Max Act: 0.6492. Min Act: -0.0000

Data Index: 1327962 (C4 (Web Text))

Max Activating Token Index: 210

Text #5

Max Range: 0.9768. Min Range: -0.9768

Max Act: 0.8199. Min Act: -0.0000

Data Index: 885813 (C4 (Web Text))

Max Activating Token Index: 761

Text #6

Max Range: 0.9768. Min Range: -0.9768

Max Act: 0.7942. Min Act: -0.0000

Data Index: 644378 (C4 (Web Text))

Max Activating Token Index: 559

Text #7

Max Range: 0.9768. Min Range: -0.9768

Max Act: 0.8168. Min Act: -0.0000

Data Index: 580268 (C4 (Web Text))

Max Activating Token Index: 787

Text #8

Max Range: 0.9768. Min Range: -0.9768

Max Act: 0.8203. Min Act: -0.0000

Data Index: 1198249 (C4 (Web Text))

Max Activating Token Index: 842

Text #9

Max Range: 0.9768. Min Range: -0.9768

Max Act: 0.6569. Min Act: -0.0000

Data Index: 1262326 (C4 (Web Text))

Max Activating Token Index: 896

Text #10

Max Range: 0.9768. Min Range: -0.9768

Max Act: 0.8182. Min Act: -0.0000

Data Index: 652443 (C4 (Web Text))

Max Activating Token Index: 759

Text #11

Max Range: 0.9768. Min Range: -0.9768

Max Act: 0.7000. Min Act: -0.0000

Data Index: 384882 (C4 (Web Text))

Max Activating Token Index: 133

Text #12

Max Range: 0.9768. Min Range: -0.9768

Max Act: 0.7841. Min Act: -0.0000

Data Index: 502221 (C4 (Web Text))

Max Activating Token Index: 740

Text #13

Max Range: 0.9768. Min Range: -0.9768

Max Act: 0.7590. Min Act: -0.0000

Data Index: 1371950 (Python Code)

Max Activating Token Index: 73

Text #14

Max Range: 0.9768. Min Range: -0.9768

Max Act: 0.6967. Min Act: -0.0000

Data Index: 431790 (C4 (Web Text))

Max Activating Token Index: 55

Text #15

Max Range: 0.9768. Min Range: -0.9768

Max Act: 0.7149. Min Act: -0.0000

Data Index: 1494376 (Python Code)

Max Activating Token Index: 500

Text #16

Max Range: 0.9768. Min Range: -0.9768

Max Act: 0.7571. Min Act: -0.0000

Data Index: 606340 (C4 (Web Text))

Max Activating Token Index: 866

Text #17

Max Range: 0.9768. Min Range: -0.9768

Max Act: 0.7351. Min Act: -0.0000

Data Index: 1138456 (C4 (Web Text))

Max Activating Token Index: 1008

Text #18

Max Range: 0.9768. Min Range: -0.9768

Max Act: 0.7032. Min Act: -0.0000

Data Index: 380214 (C4 (Web Text))

Max Activating Token Index: 28

Text #19

Max Range: 0.9768. Min Range: -0.9768

Max Act: 0.7362. Min Act: -0.0000

Data Index: 192617 (C4 (Web Text))

Max Activating Token Index: 177