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

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

Neuron 153 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5191. Min Range: -1.5191

Max Act: 1.5191. Min Act: -0.0000

Data Index: 504353 (C4 (Web Text))

Max Activating Token Index: 376

Text #1

Max Range: 1.5191. Min Range: -1.5191

Max Act: 1.3926. Min Act: -0.0000

Data Index: 652766 (C4 (Web Text))

Max Activating Token Index: 161

Text #2

Max Range: 1.5191. Min Range: -1.5191

Max Act: 1.4386. Min Act: -0.0000

Data Index: 1046620 (C4 (Web Text))

Max Activating Token Index: 184

Text #3

Max Range: 1.5191. Min Range: -1.5191

Max Act: 1.3302. Min Act: -0.0000

Data Index: 511412 (C4 (Web Text))

Max Activating Token Index: 641

Text #4

Max Range: 1.5191. Min Range: -1.5191

Max Act: 1.3760. Min Act: -0.0000

Data Index: 1242595 (C4 (Web Text))

Max Activating Token Index: 816

Text #5

Max Range: 1.5191. Min Range: -1.5191

Max Act: 1.0126. Min Act: -0.0000

Data Index: 1280534 (C4 (Web Text))

Max Activating Token Index: 589

Text #6

Max Range: 1.5191. Min Range: -1.5191

Max Act: 1.1350. Min Act: -0.0000

Data Index: 172962 (C4 (Web Text))

Max Activating Token Index: 146

Text #7

Max Range: 1.5191. Min Range: -1.5191

Max Act: 1.0627. Min Act: -0.0000

Data Index: 1056301 (C4 (Web Text))

Max Activating Token Index: 594

Text #8

Max Range: 1.5191. Min Range: -1.5191

Max Act: 1.0081. Min Act: -0.0000

Data Index: 643146 (C4 (Web Text))

Max Activating Token Index: 114

Text #9

Max Range: 1.5191. Min Range: -1.5191

Max Act: 1.0031. Min Act: -0.0000

Data Index: 436543 (C4 (Web Text))

Max Activating Token Index: 352

Text #10

Max Range: 1.5191. Min Range: -1.5191

Max Act: 0.9409. Min Act: -0.0000

Data Index: 1153014 (C4 (Web Text))

Max Activating Token Index: 743

Text #11

Max Range: 1.5191. Min Range: -1.5191

Max Act: 0.9628. Min Act: -0.0000

Data Index: 1060693 (C4 (Web Text))

Max Activating Token Index: 615

Text #12

Max Range: 1.5191. Min Range: -1.5191

Max Act: 0.8358. Min Act: -0.0000

Data Index: 256593 (C4 (Web Text))

Max Activating Token Index: 985

Text #13

Max Range: 1.5191. Min Range: -1.5191

Max Act: 0.8968. Min Act: -0.0000

Data Index: 1152013 (C4 (Web Text))

Max Activating Token Index: 714

Text #14

Max Range: 1.5191. Min Range: -1.5191

Max Act: 0.8095. Min Act: -0.0000

Data Index: 240484 (C4 (Web Text))

Max Activating Token Index: 25

Text #15

Max Range: 1.5191. Min Range: -1.5191

Max Act: 0.8539. Min Act: -0.0000

Data Index: 1020138 (C4 (Web Text))

Max Activating Token Index: 35

Text #16

Max Range: 1.5191. Min Range: -1.5191

Max Act: 0.8838. Min Act: -0.0000

Data Index: 344233 (C4 (Web Text))

Max Activating Token Index: 182

Text #17

Max Range: 1.5191. Min Range: -1.5191

Max Act: 0.8421. Min Act: -0.0000

Data Index: 904087 (C4 (Web Text))

Max Activating Token Index: 860

Text #18

Max Range: 1.5191. Min Range: -1.5191

Max Act: 0.8346. Min Act: -0.0000

Data Index: 33250 (C4 (Web Text))

Max Activating Token Index: 347

Text #19

Max Range: 1.5191. Min Range: -1.5191

Max Act: 0.7992. Min Act: -0.0000

Data Index: 607937 (C4 (Web Text))

Max Activating Token Index: 700