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

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

Neuron 1752 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.7263. Min Range: -0.7263

Max Act: 0.7263. Min Act: -0.0002

Data Index: 303301 (C4 (Web Text))

Max Activating Token Index: 11

Text #1

Max Range: 0.7263. Min Range: -0.7263

Max Act: 0.6967. Min Act: -0.0002

Data Index: 580494 (C4 (Web Text))

Max Activating Token Index: 9

Text #2

Max Range: 0.7263. Min Range: -0.7263

Max Act: 0.6523. Min Act: -0.0002

Data Index: 458108 (C4 (Web Text))

Max Activating Token Index: 17

Text #3

Max Range: 0.7263. Min Range: -0.7263

Max Act: 0.6418. Min Act: -0.0002

Data Index: 180262 (C4 (Web Text))

Max Activating Token Index: 269

Text #4

Max Range: 0.7263. Min Range: -0.7263

Max Act: 0.6478. Min Act: -0.0002

Data Index: 255360 (C4 (Web Text))

Max Activating Token Index: 130

Text #5

Max Range: 0.7263. Min Range: -0.7263

Max Act: 0.6403. Min Act: -0.0002

Data Index: 84079 (C4 (Web Text))

Max Activating Token Index: 21

Text #6

Max Range: 0.7263. Min Range: -0.7263

Max Act: 0.6231. Min Act: -0.0002

Data Index: 835910 (C4 (Web Text))

Max Activating Token Index: 2

Text #7

Max Range: 0.7263. Min Range: -0.7263

Max Act: 0.6305. Min Act: -0.0002

Data Index: 501790 (C4 (Web Text))

Max Activating Token Index: 2

Text #8

Max Range: 0.7263. Min Range: -0.7263

Max Act: 0.6305. Min Act: -0.0002

Data Index: 1354817 (C4 (Web Text))

Max Activating Token Index: 2

Text #9

Max Range: 0.7263. Min Range: -0.7263

Max Act: 0.6041. Min Act: -0.0002

Data Index: 653232 (C4 (Web Text))

Max Activating Token Index: 2

Text #10

Max Range: 0.7263. Min Range: -0.7263

Max Act: 0.6141. Min Act: -0.0002

Data Index: 64169 (C4 (Web Text))

Max Activating Token Index: 36

Text #11

Max Range: 0.7263. Min Range: -0.7263

Max Act: 0.6225. Min Act: -0.0002

Data Index: 326637 (C4 (Web Text))

Max Activating Token Index: 4

Text #12

Max Range: 0.7263. Min Range: -0.7263

Max Act: 0.6185. Min Act: -0.0002

Data Index: 87946 (C4 (Web Text))

Max Activating Token Index: 194

Text #13

Max Range: 0.7263. Min Range: -0.7263

Max Act: 0.6009. Min Act: -0.0002

Data Index: 426183 (C4 (Web Text))

Max Activating Token Index: 11

Text #14

Max Range: 0.7263. Min Range: -0.7263

Max Act: 0.5975. Min Act: -0.0002

Data Index: 1167652 (C4 (Web Text))

Max Activating Token Index: 5

Text #15

Max Range: 0.7263. Min Range: -0.7263

Max Act: 0.5873. Min Act: -0.0002

Data Index: 407061 (C4 (Web Text))

Max Activating Token Index: 41

Text #16

Max Range: 0.7263. Min Range: -0.7263

Max Act: 0.5908. Min Act: -0.0002

Data Index: 525036 (C4 (Web Text))

Max Activating Token Index: 71

Text #17

Max Range: 0.7263. Min Range: -0.7263

Max Act: 0.5809. Min Act: -0.0002

Data Index: 1328200 (C4 (Web Text))

Max Activating Token Index: 5

Text #18

Max Range: 0.7263. Min Range: -0.7263

Max Act: 0.5955. Min Act: -0.0002

Data Index: 380067 (C4 (Web Text))

Max Activating Token Index: 6

Text #19

Max Range: 0.7263. Min Range: -0.7263

Max Act: 0.5833. Min Act: -0.0002

Data Index: 872712 (C4 (Web Text))

Max Activating Token Index: 828