Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2944 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.3802. Min Range: -1.3802

Max Act: 1.3802. Min Act: -0.0001

Data Index: 966135 (C4 (Web Text))

Max Activating Token Index: 981

Text #1

Max Range: 1.3802. Min Range: -1.3802

Max Act: 1.2528. Min Act: -0.0001

Data Index: 368467 (C4 (Web Text))

Max Activating Token Index: 846

Text #2

Max Range: 1.3802. Min Range: -1.3802

Max Act: 1.0875. Min Act: -0.0001

Data Index: 41808 (C4 (Web Text))

Max Activating Token Index: 71

Text #3

Max Range: 1.3802. Min Range: -1.3802

Max Act: 1.0614. Min Act: -0.0001

Data Index: 22613 (C4 (Web Text))

Max Activating Token Index: 795

Text #4

Max Range: 1.3802. Min Range: -1.3802

Max Act: 1.0051. Min Act: -0.0001

Data Index: 1351830 (C4 (Web Text))

Max Activating Token Index: 278

Text #5

Max Range: 1.3802. Min Range: -1.3802

Max Act: 1.1148. Min Act: -0.0001

Data Index: 378141 (C4 (Web Text))

Max Activating Token Index: 323

Text #6

Max Range: 1.3802. Min Range: -1.3802

Max Act: 1.0891. Min Act: -0.0001

Data Index: 1137802 (C4 (Web Text))

Max Activating Token Index: 1007

Text #7

Max Range: 1.3802. Min Range: -1.3802

Max Act: 1.1821. Min Act: -0.0001

Data Index: 477565 (C4 (Web Text))

Max Activating Token Index: 277

Text #8

Max Range: 1.3802. Min Range: -1.3802

Max Act: 1.0682. Min Act: -0.0001

Data Index: 141125 (C4 (Web Text))

Max Activating Token Index: 154

Text #9

Max Range: 1.3802. Min Range: -1.3802

Max Act: 1.1184. Min Act: -0.0001

Data Index: 1222545 (C4 (Web Text))

Max Activating Token Index: 280

Text #10

Max Range: 1.3802. Min Range: -1.3802

Max Act: 1.0604. Min Act: -0.0001

Data Index: 731043 (C4 (Web Text))

Max Activating Token Index: 21

Text #11

Max Range: 1.3802. Min Range: -1.3802

Max Act: 1.0535. Min Act: -0.0001

Data Index: 125465 (C4 (Web Text))

Max Activating Token Index: 521

Text #12

Max Range: 1.3802. Min Range: -1.3802

Max Act: 1.0182. Min Act: -0.0001

Data Index: 158589 (C4 (Web Text))

Max Activating Token Index: 685

Text #13

Max Range: 1.3802. Min Range: -1.3802

Max Act: 0.9272. Min Act: -0.0001

Data Index: 1113083 (C4 (Web Text))

Max Activating Token Index: 161

Text #14

Max Range: 1.3802. Min Range: -1.3802

Max Act: 0.9371. Min Act: -0.0001

Data Index: 1089209 (C4 (Web Text))

Max Activating Token Index: 678

Text #15

Max Range: 1.3802. Min Range: -1.3802

Max Act: 0.9858. Min Act: -0.0001

Data Index: 886235 (C4 (Web Text))

Max Activating Token Index: 299

Text #16

Max Range: 1.3802. Min Range: -1.3802

Max Act: 0.9449. Min Act: -0.0001

Data Index: 120487 (C4 (Web Text))

Max Activating Token Index: 770

Text #17

Max Range: 1.3802. Min Range: -1.3802

Max Act: 0.9951. Min Act: -0.0001

Data Index: 1147741 (C4 (Web Text))

Max Activating Token Index: 408

Text #18

Max Range: 1.3802. Min Range: -1.3802

Max Act: 0.9299. Min Act: -0.0001

Data Index: 565338 (C4 (Web Text))

Max Activating Token Index: 416

Text #19

Max Range: 1.3802. Min Range: -1.3802

Max Act: 0.9368. Min Act: -0.0001

Data Index: 183401 (C4 (Web Text))

Max Activating Token Index: 880