Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 107 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.8213. Min Range: -0.8213

Max Act: 0.8021. Min Act: -0.0001

Data Index: 94642 (C4 (Web Text))

Max Activating Token Index: 347

Text #1

Max Range: 0.8213. Min Range: -0.8213

Max Act: 0.8213. Min Act: -0.0001

Data Index: 1249209 (C4 (Web Text))

Max Activating Token Index: 1021

Text #2

Max Range: 0.8213. Min Range: -0.8213

Max Act: 0.7871. Min Act: -0.0001

Data Index: 862914 (C4 (Web Text))

Max Activating Token Index: 686

Text #3

Max Range: 0.8213. Min Range: -0.8213

Max Act: 0.7896. Min Act: -0.0001

Data Index: 429055 (C4 (Web Text))

Max Activating Token Index: 870

Text #4

Max Range: 0.8213. Min Range: -0.8213

Max Act: 0.7235. Min Act: -0.0001

Data Index: 1176019 (C4 (Web Text))

Max Activating Token Index: 636

Text #5

Max Range: 0.8213. Min Range: -0.8213

Max Act: 0.7295. Min Act: -0.0001

Data Index: 236187 (C4 (Web Text))

Max Activating Token Index: 372

Text #6

Max Range: 0.8213. Min Range: -0.8213

Max Act: 0.6553. Min Act: -0.0001

Data Index: 198521 (C4 (Web Text))

Max Activating Token Index: 922

Text #7

Max Range: 0.8213. Min Range: -0.8213

Max Act: 0.6649. Min Act: -0.0001

Data Index: 767232 (C4 (Web Text))

Max Activating Token Index: 909

Text #8

Max Range: 0.8213. Min Range: -0.8213

Max Act: 0.6157. Min Act: -0.0001

Data Index: 222864 (C4 (Web Text))

Max Activating Token Index: 700

Text #9

Max Range: 0.8213. Min Range: -0.8213

Max Act: 0.6398. Min Act: -0.0001

Data Index: 370257 (C4 (Web Text))

Max Activating Token Index: 304

Text #10

Max Range: 0.8213. Min Range: -0.8213

Max Act: 0.6209. Min Act: -0.0001

Data Index: 131757 (C4 (Web Text))

Max Activating Token Index: 82

Text #11

Max Range: 0.8213. Min Range: -0.8213

Max Act: 0.6129. Min Act: -0.0001

Data Index: 1225485 (C4 (Web Text))

Max Activating Token Index: 800

Text #12

Max Range: 0.8213. Min Range: -0.8213

Max Act: 0.6244. Min Act: -0.0001

Data Index: 169898 (C4 (Web Text))

Max Activating Token Index: 931

Text #13

Max Range: 0.8213. Min Range: -0.8213

Max Act: 0.6062. Min Act: -0.0001

Data Index: 369966 (C4 (Web Text))

Max Activating Token Index: 996

Text #14

Max Range: 0.8213. Min Range: -0.8213

Max Act: 0.6415. Min Act: -0.0001

Data Index: 201373 (C4 (Web Text))

Max Activating Token Index: 388

Text #15

Max Range: 0.8213. Min Range: -0.8213

Max Act: 0.4820. Min Act: -0.0001

Data Index: 1117079 (C4 (Web Text))

Max Activating Token Index: 619

Text #16

Max Range: 0.8213. Min Range: -0.8213

Max Act: 0.5908. Min Act: -0.0001

Data Index: 787973 (C4 (Web Text))

Max Activating Token Index: 43

Text #17

Max Range: 0.8213. Min Range: -0.8213

Max Act: 0.5552. Min Act: -0.0001

Data Index: 651140 (C4 (Web Text))

Max Activating Token Index: 304

Text #18

Max Range: 0.8213. Min Range: -0.8213

Max Act: 0.5839. Min Act: -0.0001

Data Index: 357195 (C4 (Web Text))

Max Activating Token Index: 530

Text #19

Max Range: 0.8213. Min Range: -0.8213

Max Act: 0.5679. Min Act: -0.0001

Data Index: 1217881 (C4 (Web Text))

Max Activating Token Index: 40