Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 933 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.7582. Min Range: -1.7582

Max Act: 1.7582. Min Act: -0.0002

Data Index: 756217 (C4 (Web Text))

Max Activating Token Index: 327

Text #1

Max Range: 1.7582. Min Range: -1.7582

Max Act: 1.7391. Min Act: -0.0001

Data Index: 326932 (C4 (Web Text))

Max Activating Token Index: 96

Text #2

Max Range: 1.7582. Min Range: -1.7582

Max Act: 1.6501. Min Act: -0.0001

Data Index: 242471 (C4 (Web Text))

Max Activating Token Index: 973

Text #3

Max Range: 1.7582. Min Range: -1.7582

Max Act: 1.5773. Min Act: -0.0001

Data Index: 56104 (C4 (Web Text))

Max Activating Token Index: 252

Text #4

Max Range: 1.7582. Min Range: -1.7582

Max Act: 1.6220. Min Act: -0.0001

Data Index: 931209 (C4 (Web Text))

Max Activating Token Index: 64

Text #5

Max Range: 1.7582. Min Range: -1.7582

Max Act: 1.5124. Min Act: -0.0001

Data Index: 821842 (C4 (Web Text))

Max Activating Token Index: 492

Text #6

Max Range: 1.7582. Min Range: -1.7582

Max Act: 1.5041. Min Act: -0.0001

Data Index: 399523 (C4 (Web Text))

Max Activating Token Index: 539

Text #7

Max Range: 1.7582. Min Range: -1.7582

Max Act: 1.5524. Min Act: -0.0001

Data Index: 324122 (C4 (Web Text))

Max Activating Token Index: 136

Text #8

Max Range: 1.7582. Min Range: -1.7582

Max Act: 1.5482. Min Act: -0.0001

Data Index: 720383 (C4 (Web Text))

Max Activating Token Index: 417

Text #9

Max Range: 1.7582. Min Range: -1.7582

Max Act: 1.4817. Min Act: -0.0001

Data Index: 175179 (C4 (Web Text))

Max Activating Token Index: 50

Text #10

Max Range: 1.7582. Min Range: -1.7582

Max Act: 1.4698. Min Act: -0.0002

Data Index: 650321 (C4 (Web Text))

Max Activating Token Index: 444

Text #11

Max Range: 1.7582. Min Range: -1.7582

Max Act: 1.3938. Min Act: -0.0001

Data Index: 673691 (C4 (Web Text))

Max Activating Token Index: 698

Text #12

Max Range: 1.7582. Min Range: -1.7582

Max Act: 1.5210. Min Act: -0.0002

Data Index: 265520 (C4 (Web Text))

Max Activating Token Index: 235

Text #13

Max Range: 1.7582. Min Range: -1.7582

Max Act: 1.4932. Min Act: -0.0002

Data Index: 183065 (C4 (Web Text))

Max Activating Token Index: 141

Text #14

Max Range: 1.7582. Min Range: -1.7582

Max Act: 1.4531. Min Act: -0.0002

Data Index: 537874 (C4 (Web Text))

Max Activating Token Index: 41

Text #15

Max Range: 1.7582. Min Range: -1.7582

Max Act: 1.3926. Min Act: -0.0001

Data Index: 260123 (C4 (Web Text))

Max Activating Token Index: 173

Text #16

Max Range: 1.7582. Min Range: -1.7582

Max Act: 1.3706. Min Act: -0.0001

Data Index: 97453 (C4 (Web Text))

Max Activating Token Index: 9

Text #17

Max Range: 1.7582. Min Range: -1.7582

Max Act: 1.3768. Min Act: -0.0001

Data Index: 256233 (C4 (Web Text))

Max Activating Token Index: 578

Text #18

Max Range: 1.7582. Min Range: -1.7582

Max Act: 1.4071. Min Act: -0.0001

Data Index: 1257275 (C4 (Web Text))

Max Activating Token Index: 882

Text #19

Max Range: 1.7582. Min Range: -1.7582

Max Act: 1.4383. Min Act: -0.0001

Data Index: 1126942 (C4 (Web Text))

Max Activating Token Index: 102