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

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

Neuron 2397 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1356. Min Range: -0.1356

Max Act: 0.1356. Min Act: -0.0002

Data Index: 646092 (C4 (Web Text))

Max Activating Token Index: 405

Text #1

Max Range: 0.1356. Min Range: -0.1356

Max Act: 0.1223. Min Act: -0.0002

Data Index: 818188 (C4 (Web Text))

Max Activating Token Index: 335

Text #2

Max Range: 0.1356. Min Range: -0.1356

Max Act: 0.1234. Min Act: -0.0002

Data Index: 417193 (C4 (Web Text))

Max Activating Token Index: 330

Text #3

Max Range: 0.1356. Min Range: -0.1356

Max Act: 0.1075. Min Act: -0.0002

Data Index: 260948 (C4 (Web Text))

Max Activating Token Index: 876

Text #4

Max Range: 0.1356. Min Range: -0.1356

Max Act: 0.1086. Min Act: -0.0002

Data Index: 428818 (C4 (Web Text))

Max Activating Token Index: 315

Text #5

Max Range: 0.1356. Min Range: -0.1356

Max Act: 0.1011. Min Act: -0.0003

Data Index: 588002 (C4 (Web Text))

Max Activating Token Index: 409

Text #6

Max Range: 0.1356. Min Range: -0.1356

Max Act: 0.0981. Min Act: -0.0002

Data Index: 978479 (C4 (Web Text))

Max Activating Token Index: 4

Text #7

Max Range: 0.1356. Min Range: -0.1356

Max Act: 0.1004. Min Act: -0.0002

Data Index: 1028206 (C4 (Web Text))

Max Activating Token Index: 50

Text #8

Max Range: 0.1356. Min Range: -0.1356

Max Act: 0.0979. Min Act: -0.0002

Data Index: 957332 (C4 (Web Text))

Max Activating Token Index: 146

Text #9

Max Range: 0.1356. Min Range: -0.1356

Max Act: 0.0996. Min Act: -0.0002

Data Index: 1100585 (C4 (Web Text))

Max Activating Token Index: 479

Text #10

Max Range: 0.1356. Min Range: -0.1356

Max Act: 0.0930. Min Act: -0.0002

Data Index: 1185189 (C4 (Web Text))

Max Activating Token Index: 448

Text #11

Max Range: 0.1356. Min Range: -0.1356

Max Act: 0.0952. Min Act: -0.0002

Data Index: 965249 (C4 (Web Text))

Max Activating Token Index: 129

Text #12

Max Range: 0.1356. Min Range: -0.1356

Max Act: 0.0899. Min Act: -0.0002

Data Index: 290626 (C4 (Web Text))

Max Activating Token Index: 134

Text #13

Max Range: 0.1356. Min Range: -0.1356

Max Act: 0.0901. Min Act: -0.0002

Data Index: 1262586 (C4 (Web Text))

Max Activating Token Index: 19

Text #14

Max Range: 0.1356. Min Range: -0.1356

Max Act: 0.0917. Min Act: -0.0002

Data Index: 1331733 (C4 (Web Text))

Max Activating Token Index: 34

Text #15

Max Range: 0.1356. Min Range: -0.1356

Max Act: 0.1056. Min Act: -0.0002

Data Index: 259327 (C4 (Web Text))

Max Activating Token Index: 894

Text #16

Max Range: 0.1356. Min Range: -0.1356

Max Act: 0.0905. Min Act: -0.0002

Data Index: 1216563 (C4 (Web Text))

Max Activating Token Index: 157

Text #17

Max Range: 0.1356. Min Range: -0.1356

Max Act: 0.0939. Min Act: -0.0002

Data Index: 1523829 (Python Code)

Max Activating Token Index: 710

Text #18

Max Range: 0.1356. Min Range: -0.1356

Max Act: 0.0870. Min Act: -0.0002

Data Index: 1244218 (C4 (Web Text))

Max Activating Token Index: 157

Text #19

Max Range: 0.1356. Min Range: -0.1356

Max Act: 0.0936. Min Act: -0.0002

Data Index: 1026971 (C4 (Web Text))

Max Activating Token Index: 453