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

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

Neuron 3845 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: 0.5889. Min Range: -0.5889

Max Act: 0.5889. Min Act: -0.0002

Data Index: 743238 (C4 (Web Text))

Max Activating Token Index: 153

Text #1

Max Range: 0.5889. Min Range: -0.5889

Max Act: 0.5569. Min Act: -0.0002

Data Index: 220379 (C4 (Web Text))

Max Activating Token Index: 526

Text #2

Max Range: 0.5889. Min Range: -0.5889

Max Act: 0.5565. Min Act: -0.0002

Data Index: 999580 (C4 (Web Text))

Max Activating Token Index: 233

Text #3

Max Range: 0.5889. Min Range: -0.5889

Max Act: 0.5565. Min Act: -0.0002

Data Index: 217603 (C4 (Web Text))

Max Activating Token Index: 429

Text #4

Max Range: 0.5889. Min Range: -0.5889

Max Act: 0.5431. Min Act: -0.0002

Data Index: 788707 (C4 (Web Text))

Max Activating Token Index: 292

Text #5

Max Range: 0.5889. Min Range: -0.5889

Max Act: 0.5409. Min Act: -0.0002

Data Index: 537798 (C4 (Web Text))

Max Activating Token Index: 1010

Text #6

Max Range: 0.5889. Min Range: -0.5889

Max Act: 0.5210. Min Act: -0.0002

Data Index: 782970 (C4 (Web Text))

Max Activating Token Index: 641

Text #7

Max Range: 0.5889. Min Range: -0.5889

Max Act: 0.5207. Min Act: -0.0002

Data Index: 98609 (C4 (Web Text))

Max Activating Token Index: 221

Text #8

Max Range: 0.5889. Min Range: -0.5889

Max Act: 0.5301. Min Act: -0.0002

Data Index: 477540 (C4 (Web Text))

Max Activating Token Index: 413

Text #9

Max Range: 0.5889. Min Range: -0.5889

Max Act: 0.5225. Min Act: -0.0002

Data Index: 196194 (C4 (Web Text))

Max Activating Token Index: 261

Text #10

Max Range: 0.5889. Min Range: -0.5889

Max Act: 0.5190. Min Act: -0.0002

Data Index: 1251224 (C4 (Web Text))

Max Activating Token Index: 460

Text #11

Max Range: 0.5889. Min Range: -0.5889

Max Act: 0.5254. Min Act: -0.0002

Data Index: 36205 (C4 (Web Text))

Max Activating Token Index: 86

Text #12

Max Range: 0.5889. Min Range: -0.5889

Max Act: 0.5271. Min Act: -0.0002

Data Index: 814211 (C4 (Web Text))

Max Activating Token Index: 38

Text #13

Max Range: 0.5889. Min Range: -0.5889

Max Act: 0.4975. Min Act: -0.0002

Data Index: 263790 (C4 (Web Text))

Max Activating Token Index: 775

Text #14

Max Range: 0.5889. Min Range: -0.5889

Max Act: 0.5122. Min Act: -0.0002

Data Index: 367141 (C4 (Web Text))

Max Activating Token Index: 793

Text #15

Max Range: 0.5889. Min Range: -0.5889

Max Act: 0.5117. Min Act: -0.0002

Data Index: 437258 (C4 (Web Text))

Max Activating Token Index: 851

Text #16

Max Range: 0.5889. Min Range: -0.5889

Max Act: 0.5054. Min Act: -0.0002

Data Index: 1220912 (C4 (Web Text))

Max Activating Token Index: 934

Text #17

Max Range: 0.5889. Min Range: -0.5889

Max Act: 0.4992. Min Act: -0.0002

Data Index: 154694 (C4 (Web Text))

Max Activating Token Index: 21

Text #18

Max Range: 0.5889. Min Range: -0.5889

Max Act: 0.4970. Min Act: -0.0002

Data Index: 830566 (C4 (Web Text))

Max Activating Token Index: 134

Text #19

Max Range: 0.5889. Min Range: -0.5889

Max Act: 0.5002. Min Act: -0.0002

Data Index: 60970 (C4 (Web Text))

Max Activating Token Index: 446