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

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

Neuron 4466 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.9163. Min Range: -4.9163

Max Act: 4.7935. Min Act: -0.0000

Data Index: 179342 (C4 (Web Text))

Max Activating Token Index: 437

Text #1

Max Range: 4.9163. Min Range: -4.9163

Max Act: 4.7331. Min Act: -0.0000

Data Index: 270020 (C4 (Web Text))

Max Activating Token Index: 619

Text #2

Max Range: 4.9163. Min Range: -4.9163

Max Act: 4.6649. Min Act: -0.0000

Data Index: 1275471 (C4 (Web Text))

Max Activating Token Index: 572

Text #3

Max Range: 4.9163. Min Range: -4.9163

Max Act: 4.9163. Min Act: -0.0000

Data Index: 271618 (C4 (Web Text))

Max Activating Token Index: 178

Text #4

Max Range: 4.9163. Min Range: -4.9163

Max Act: 2.1675. Min Act: -0.0000

Data Index: 934139 (C4 (Web Text))

Max Activating Token Index: 204

Text #5

Max Range: 4.9163. Min Range: -4.9163

Max Act: 1.5877. Min Act: -0.0000

Data Index: 26685 (C4 (Web Text))

Max Activating Token Index: 136

Text #6

Max Range: 4.9163. Min Range: -4.9163

Max Act: 1.1932. Min Act: -0.0000

Data Index: 674186 (C4 (Web Text))

Max Activating Token Index: 992

Text #7

Max Range: 4.9163. Min Range: -4.9163

Max Act: 1.0116. Min Act: -0.0000

Data Index: 384050 (C4 (Web Text))

Max Activating Token Index: 31

Text #8

Max Range: 4.9163. Min Range: -4.9163

Max Act: 0.8070. Min Act: -0.0000

Data Index: 1065604 (C4 (Web Text))

Max Activating Token Index: 843

Text #9

Max Range: 4.9163. Min Range: -4.9163

Max Act: 0.7762. Min Act: -0.0000

Data Index: 952241 (C4 (Web Text))

Max Activating Token Index: 218

Text #10

Max Range: 4.9163. Min Range: -4.9163

Max Act: 0.7179. Min Act: -0.0000

Data Index: 542909 (C4 (Web Text))

Max Activating Token Index: 822

Text #11

Max Range: 4.9163. Min Range: -4.9163

Max Act: 0.7930. Min Act: -0.0000

Data Index: 1101221 (C4 (Web Text))

Max Activating Token Index: 972

Text #12

Max Range: 4.9163. Min Range: -4.9163

Max Act: 0.7505. Min Act: -0.0000

Data Index: 316408 (C4 (Web Text))

Max Activating Token Index: 393

Text #13

Max Range: 4.9163. Min Range: -4.9163

Max Act: 0.6684. Min Act: -0.0000

Data Index: 1127677 (C4 (Web Text))

Max Activating Token Index: 780

Text #14

Max Range: 4.9163. Min Range: -4.9163

Max Act: 0.7505. Min Act: -0.0000

Data Index: 991320 (C4 (Web Text))

Max Activating Token Index: 372

Text #15

Max Range: 4.9163. Min Range: -4.9163

Max Act: 0.6656. Min Act: -0.0000

Data Index: 602904 (C4 (Web Text))

Max Activating Token Index: 84

Text #16

Max Range: 4.9163. Min Range: -4.9163

Max Act: 0.7073. Min Act: -0.0000

Data Index: 761952 (C4 (Web Text))

Max Activating Token Index: 928

Text #17

Max Range: 4.9163. Min Range: -4.9163

Max Act: 0.6776. Min Act: -0.0000

Data Index: 1325772 (C4 (Web Text))

Max Activating Token Index: 302

Text #18

Max Range: 4.9163. Min Range: -4.9163

Max Act: 0.6647. Min Act: -0.0000

Data Index: 392059 (C4 (Web Text))

Max Activating Token Index: 12

Text #19

Max Range: 4.9163. Min Range: -4.9163

Max Act: 0.5893. Min Act: -0.0000

Data Index: 103343 (C4 (Web Text))

Max Activating Token Index: 1004