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

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

Neuron 1809 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2796. Min Range: -0.2796

Max Act: 0.2572. Min Act: -0.0000

Data Index: 434893 (C4 (Web Text))

Max Activating Token Index: 1000

Text #1

Max Range: 0.2796. Min Range: -0.2796

Max Act: 0.2655. Min Act: -0.0000

Data Index: 716012 (C4 (Web Text))

Max Activating Token Index: 384

Text #2

Max Range: 0.2796. Min Range: -0.2796

Max Act: 0.2796. Min Act: -0.0000

Data Index: 537642 (C4 (Web Text))

Max Activating Token Index: 245

Text #3

Max Range: 0.2796. Min Range: -0.2796

Max Act: 0.2624. Min Act: -0.0000

Data Index: 17676 (C4 (Web Text))

Max Activating Token Index: 418

Text #4

Max Range: 0.2796. Min Range: -0.2796

Max Act: 0.2204. Min Act: -0.0000

Data Index: 440447 (C4 (Web Text))

Max Activating Token Index: 283

Text #5

Max Range: 0.2796. Min Range: -0.2796

Max Act: 0.2553. Min Act: -0.0000

Data Index: 276854 (C4 (Web Text))

Max Activating Token Index: 546

Text #6

Max Range: 0.2796. Min Range: -0.2796

Max Act: 0.2362. Min Act: -0.0000

Data Index: 733646 (C4 (Web Text))

Max Activating Token Index: 877

Text #7

Max Range: 0.2796. Min Range: -0.2796

Max Act: 0.2100. Min Act: -0.0000

Data Index: 379481 (C4 (Web Text))

Max Activating Token Index: 936

Text #8

Max Range: 0.2796. Min Range: -0.2796

Max Act: 0.1863. Min Act: -0.0000

Data Index: 564197 (C4 (Web Text))

Max Activating Token Index: 782

Text #9

Max Range: 0.2796. Min Range: -0.2796

Max Act: 0.2259. Min Act: -0.0000

Data Index: 294549 (C4 (Web Text))

Max Activating Token Index: 1016

Text #10

Max Range: 0.2796. Min Range: -0.2796

Max Act: 0.2292. Min Act: -0.0000

Data Index: 341089 (C4 (Web Text))

Max Activating Token Index: 811

Text #11

Max Range: 0.2796. Min Range: -0.2796

Max Act: 0.2271. Min Act: -0.0000

Data Index: 909177 (C4 (Web Text))

Max Activating Token Index: 46

Text #12

Max Range: 0.2796. Min Range: -0.2796

Max Act: 0.2131. Min Act: -0.0000

Data Index: 1078049 (C4 (Web Text))

Max Activating Token Index: 824

Text #13

Max Range: 0.2796. Min Range: -0.2796

Max Act: 0.1940. Min Act: -0.0000

Data Index: 27022 (C4 (Web Text))

Max Activating Token Index: 969

Text #14

Max Range: 0.2796. Min Range: -0.2796

Max Act: 0.2194. Min Act: -0.0000

Data Index: 5575 (C4 (Web Text))

Max Activating Token Index: 796

Text #15

Max Range: 0.2796. Min Range: -0.2796

Max Act: 0.2206. Min Act: -0.0000

Data Index: 1488222 (Python Code)

Max Activating Token Index: 507

Text #16

Max Range: 0.2796. Min Range: -0.2796

Max Act: 0.1688. Min Act: -0.0000

Data Index: 273956 (C4 (Web Text))

Max Activating Token Index: 431

Text #17

Max Range: 0.2796. Min Range: -0.2796

Max Act: 0.2129. Min Act: -0.0000

Data Index: 922943 (C4 (Web Text))

Max Activating Token Index: 152

Text #18

Max Range: 0.2796. Min Range: -0.2796

Max Act: 0.1988. Min Act: -0.0000

Data Index: 427755 (C4 (Web Text))

Max Activating Token Index: 1014

Text #19

Max Range: 0.2796. Min Range: -0.2796

Max Act: 0.1953. Min Act: -0.0000

Data Index: 288123 (C4 (Web Text))

Max Activating Token Index: 979