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

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

Neuron 4 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: 1.6256. Min Range: -1.6256

Max Act: 1.6256. Min Act: -0.0002

Data Index: 1086113 (C4 (Web Text))

Max Activating Token Index: 798

Text #1

Max Range: 1.6256. Min Range: -1.6256

Max Act: 1.5791. Min Act: -0.0002

Data Index: 759098 (C4 (Web Text))

Max Activating Token Index: 258

Text #2

Max Range: 1.6256. Min Range: -1.6256

Max Act: 1.5079. Min Act: -0.0002

Data Index: 84475 (C4 (Web Text))

Max Activating Token Index: 120

Text #3

Max Range: 1.6256. Min Range: -1.6256

Max Act: 1.4884. Min Act: -0.0002

Data Index: 624418 (C4 (Web Text))

Max Activating Token Index: 381

Text #4

Max Range: 1.6256. Min Range: -1.6256

Max Act: 1.4833. Min Act: -0.0002

Data Index: 1287409 (C4 (Web Text))

Max Activating Token Index: 80

Text #5

Max Range: 1.6256. Min Range: -1.6256

Max Act: 1.4406. Min Act: -0.0002

Data Index: 115374 (C4 (Web Text))

Max Activating Token Index: 226

Text #6

Max Range: 1.6256. Min Range: -1.6256

Max Act: 1.4252. Min Act: -0.0002

Data Index: 364723 (C4 (Web Text))

Max Activating Token Index: 832

Text #7

Max Range: 1.6256. Min Range: -1.6256

Max Act: 1.4345. Min Act: -0.0003

Data Index: 731158 (C4 (Web Text))

Max Activating Token Index: 726

Text #8

Max Range: 1.6256. Min Range: -1.6256

Max Act: 1.3952. Min Act: -0.0002

Data Index: 206862 (C4 (Web Text))

Max Activating Token Index: 417

Text #9

Max Range: 1.6256. Min Range: -1.6256

Max Act: 1.3831. Min Act: -0.0002

Data Index: 1277401 (C4 (Web Text))

Max Activating Token Index: 874

Text #10

Max Range: 1.6256. Min Range: -1.6256

Max Act: 1.4217. Min Act: -0.0002

Data Index: 62951 (C4 (Web Text))

Max Activating Token Index: 117

Text #11

Max Range: 1.6256. Min Range: -1.6256

Max Act: 1.4021. Min Act: -0.0002

Data Index: 1036021 (C4 (Web Text))

Max Activating Token Index: 469

Text #12

Max Range: 1.6256. Min Range: -1.6256

Max Act: 1.3695. Min Act: -0.0002

Data Index: 190070 (C4 (Web Text))

Max Activating Token Index: 212

Text #13

Max Range: 1.6256. Min Range: -1.6256

Max Act: 1.3709. Min Act: -0.0002

Data Index: 26585 (C4 (Web Text))

Max Activating Token Index: 848

Text #14

Max Range: 1.6256. Min Range: -1.6256

Max Act: 1.3709. Min Act: -0.0002

Data Index: 710579 (C4 (Web Text))

Max Activating Token Index: 711

Text #15

Max Range: 1.6256. Min Range: -1.6256

Max Act: 1.3761. Min Act: -0.0002

Data Index: 1035353 (C4 (Web Text))

Max Activating Token Index: 263

Text #16

Max Range: 1.6256. Min Range: -1.6256

Max Act: 1.3814. Min Act: -0.0002

Data Index: 532957 (C4 (Web Text))

Max Activating Token Index: 150

Text #17

Max Range: 1.6256. Min Range: -1.6256

Max Act: 1.3655. Min Act: -0.0002

Data Index: 705680 (C4 (Web Text))

Max Activating Token Index: 884

Text #18

Max Range: 1.6256. Min Range: -1.6256

Max Act: 1.3697. Min Act: -0.0002

Data Index: 1180070 (C4 (Web Text))

Max Activating Token Index: 915

Text #19

Max Range: 1.6256. Min Range: -1.6256

Max Act: 1.3721. Min Act: -0.0002

Data Index: 267215 (C4 (Web Text))

Max Activating Token Index: 871