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

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

Neuron 3623 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.4196. Min Range: -1.4196

Max Act: 1.4196. Min Act: -0.0001

Data Index: 987237 (C4 (Web Text))

Max Activating Token Index: 164

Text #1

Max Range: 1.4196. Min Range: -1.4196

Max Act: 1.3136. Min Act: -0.0001

Data Index: 656407 (C4 (Web Text))

Max Activating Token Index: 582

Text #2

Max Range: 1.4196. Min Range: -1.4196

Max Act: 1.3041. Min Act: -0.0001

Data Index: 694 (C4 (Web Text))

Max Activating Token Index: 607

Text #3

Max Range: 1.4196. Min Range: -1.4196

Max Act: 1.1880. Min Act: -0.0001

Data Index: 907218 (C4 (Web Text))

Max Activating Token Index: 936

Text #4

Max Range: 1.4196. Min Range: -1.4196

Max Act: 1.2702. Min Act: -0.0001

Data Index: 392671 (C4 (Web Text))

Max Activating Token Index: 673

Text #5

Max Range: 1.4196. Min Range: -1.4196

Max Act: 1.2510. Min Act: -0.0001

Data Index: 132277 (C4 (Web Text))

Max Activating Token Index: 322

Text #6

Max Range: 1.4196. Min Range: -1.4196

Max Act: 1.3279. Min Act: -0.0001

Data Index: 1180305 (C4 (Web Text))

Max Activating Token Index: 137

Text #7

Max Range: 1.4196. Min Range: -1.4196

Max Act: 1.1920. Min Act: -0.0001

Data Index: 769261 (C4 (Web Text))

Max Activating Token Index: 178

Text #8

Max Range: 1.4196. Min Range: -1.4196

Max Act: 1.1224. Min Act: -0.0001

Data Index: 1204968 (C4 (Web Text))

Max Activating Token Index: 761

Text #9

Max Range: 1.4196. Min Range: -1.4196

Max Act: 1.0922. Min Act: -0.0001

Data Index: 1230627 (C4 (Web Text))

Max Activating Token Index: 857

Text #10

Max Range: 1.4196. Min Range: -1.4196

Max Act: 1.1156. Min Act: -0.0001

Data Index: 1143837 (C4 (Web Text))

Max Activating Token Index: 561

Text #11

Max Range: 1.4196. Min Range: -1.4196

Max Act: 1.0515. Min Act: -0.0001

Data Index: 703851 (C4 (Web Text))

Max Activating Token Index: 578

Text #12

Max Range: 1.4196. Min Range: -1.4196

Max Act: 1.0740. Min Act: -0.0001

Data Index: 964651 (C4 (Web Text))

Max Activating Token Index: 90

Text #13

Max Range: 1.4196. Min Range: -1.4196

Max Act: 1.0965. Min Act: -0.0001

Data Index: 1487534 (Python Code)

Max Activating Token Index: 807

Text #14

Max Range: 1.4196. Min Range: -1.4196

Max Act: 1.0798. Min Act: -0.0001

Data Index: 329103 (C4 (Web Text))

Max Activating Token Index: 88

Text #15

Max Range: 1.4196. Min Range: -1.4196

Max Act: 1.0273. Min Act: -0.0001

Data Index: 1564791 (Python Code)

Max Activating Token Index: 812

Text #16

Max Range: 1.4196. Min Range: -1.4196

Max Act: 1.1066. Min Act: -0.0001

Data Index: 1479343 (Python Code)

Max Activating Token Index: 644

Text #17

Max Range: 1.4196. Min Range: -1.4196

Max Act: 1.0749. Min Act: -0.0001

Data Index: 1277 (C4 (Web Text))

Max Activating Token Index: 65

Text #18

Max Range: 1.4196. Min Range: -1.4196

Max Act: 1.0196. Min Act: -0.0001

Data Index: 346187 (C4 (Web Text))

Max Activating Token Index: 953

Text #19

Max Range: 1.4196. Min Range: -1.4196

Max Act: 1.0439. Min Act: -0.0001

Data Index: 328019 (C4 (Web Text))

Max Activating Token Index: 495