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

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

Neuron 4621 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: 1.2727. Min Range: -1.2727

Max Act: 1.2727. Min Act: -0.0002

Data Index: 65510 (C4 (Web Text))

Max Activating Token Index: 682

Text #1

Max Range: 1.2727. Min Range: -1.2727

Max Act: 1.1782. Min Act: -0.0002

Data Index: 947400 (C4 (Web Text))

Max Activating Token Index: 13

Text #2

Max Range: 1.2727. Min Range: -1.2727

Max Act: 1.1298. Min Act: -0.0002

Data Index: 1183117 (C4 (Web Text))

Max Activating Token Index: 888

Text #3

Max Range: 1.2727. Min Range: -1.2727

Max Act: 1.0808. Min Act: -0.0002

Data Index: 794498 (C4 (Web Text))

Max Activating Token Index: 55

Text #4

Max Range: 1.2727. Min Range: -1.2727

Max Act: 1.0753. Min Act: -0.0002

Data Index: 998853 (C4 (Web Text))

Max Activating Token Index: 905

Text #5

Max Range: 1.2727. Min Range: -1.2727

Max Act: 1.0829. Min Act: -0.0002

Data Index: 667832 (C4 (Web Text))

Max Activating Token Index: 329

Text #6

Max Range: 1.2727. Min Range: -1.2727

Max Act: 1.0672. Min Act: -0.0002

Data Index: 644835 (C4 (Web Text))

Max Activating Token Index: 991

Text #7

Max Range: 1.2727. Min Range: -1.2727

Max Act: 1.0710. Min Act: -0.0002

Data Index: 827272 (C4 (Web Text))

Max Activating Token Index: 95

Text #8

Max Range: 1.2727. Min Range: -1.2727

Max Act: 1.0521. Min Act: -0.0002

Data Index: 304602 (C4 (Web Text))

Max Activating Token Index: 916

Text #9

Max Range: 1.2727. Min Range: -1.2727

Max Act: 1.0727. Min Act: -0.0002

Data Index: 116263 (C4 (Web Text))

Max Activating Token Index: 267

Text #10

Max Range: 1.2727. Min Range: -1.2727

Max Act: 1.0474. Min Act: -0.0002

Data Index: 762063 (C4 (Web Text))

Max Activating Token Index: 864

Text #11

Max Range: 1.2727. Min Range: -1.2727

Max Act: 1.0509. Min Act: -0.0002

Data Index: 171385 (C4 (Web Text))

Max Activating Token Index: 39

Text #12

Max Range: 1.2727. Min Range: -1.2727

Max Act: 1.0530. Min Act: -0.0002

Data Index: 1066199 (C4 (Web Text))

Max Activating Token Index: 582

Text #13

Max Range: 1.2727. Min Range: -1.2727

Max Act: 1.0438. Min Act: -0.0002

Data Index: 20362 (C4 (Web Text))

Max Activating Token Index: 89

Text #14

Max Range: 1.2727. Min Range: -1.2727

Max Act: 1.0281. Min Act: -0.0002

Data Index: 166710 (C4 (Web Text))

Max Activating Token Index: 46

Text #15

Max Range: 1.2727. Min Range: -1.2727

Max Act: 1.0476. Min Act: -0.0002

Data Index: 985439 (C4 (Web Text))

Max Activating Token Index: 324

Text #16

Max Range: 1.2727. Min Range: -1.2727

Max Act: 1.0405. Min Act: -0.0002

Data Index: 29287 (C4 (Web Text))

Max Activating Token Index: 149

Text #17

Max Range: 1.2727. Min Range: -1.2727

Max Act: 1.0537. Min Act: -0.0002

Data Index: 1103472 (C4 (Web Text))

Max Activating Token Index: 211

Text #18

Max Range: 1.2727. Min Range: -1.2727

Max Act: 1.0402. Min Act: -0.0002

Data Index: 1119318 (C4 (Web Text))

Max Activating Token Index: 128

Text #19

Max Range: 1.2727. Min Range: -1.2727

Max Act: 1.0504. Min Act: -0.0002

Data Index: 940964 (C4 (Web Text))

Max Activating Token Index: 790