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

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

Neuron 4720 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6070. Min Range: -1.6070

Max Act: 1.5610. Min Act: -0.0000

Data Index: 768197 (C4 (Web Text))

Max Activating Token Index: 636

Text #1

Max Range: 1.6070. Min Range: -1.6070

Max Act: 1.6070. Min Act: -0.0000

Data Index: 730779 (C4 (Web Text))

Max Activating Token Index: 957

Text #2

Max Range: 1.6070. Min Range: -1.6070

Max Act: 1.5336. Min Act: -0.0000

Data Index: 32422 (C4 (Web Text))

Max Activating Token Index: 447

Text #3

Max Range: 1.6070. Min Range: -1.6070

Max Act: 1.4557. Min Act: -0.0000

Data Index: 1077678 (C4 (Web Text))

Max Activating Token Index: 976

Text #4

Max Range: 1.6070. Min Range: -1.6070

Max Act: 1.5208. Min Act: -0.0000

Data Index: 776794 (C4 (Web Text))

Max Activating Token Index: 582

Text #5

Max Range: 1.6070. Min Range: -1.6070

Max Act: 1.2959. Min Act: -0.0000

Data Index: 884418 (C4 (Web Text))

Max Activating Token Index: 893

Text #6

Max Range: 1.6070. Min Range: -1.6070

Max Act: 1.2259. Min Act: -0.0000

Data Index: 129458 (C4 (Web Text))

Max Activating Token Index: 1022

Text #7

Max Range: 1.6070. Min Range: -1.6070

Max Act: 1.2249. Min Act: -0.0000

Data Index: 1018446 (C4 (Web Text))

Max Activating Token Index: 97

Text #8

Max Range: 1.6070. Min Range: -1.6070

Max Act: 1.1246. Min Act: -0.0000

Data Index: 571914 (C4 (Web Text))

Max Activating Token Index: 999

Text #9

Max Range: 1.6070. Min Range: -1.6070

Max Act: 1.1855. Min Act: -0.0000

Data Index: 723984 (C4 (Web Text))

Max Activating Token Index: 501

Text #10

Max Range: 1.6070. Min Range: -1.6070

Max Act: 1.1033. Min Act: -0.0000

Data Index: 206938 (C4 (Web Text))

Max Activating Token Index: 790

Text #11

Max Range: 1.6070. Min Range: -1.6070

Max Act: 1.2784. Min Act: -0.0000

Data Index: 680336 (C4 (Web Text))

Max Activating Token Index: 894

Text #12

Max Range: 1.6070. Min Range: -1.6070

Max Act: 1.2042. Min Act: -0.0000

Data Index: 604955 (C4 (Web Text))

Max Activating Token Index: 806

Text #13

Max Range: 1.6070. Min Range: -1.6070

Max Act: 1.1988. Min Act: -0.0000

Data Index: 840352 (C4 (Web Text))

Max Activating Token Index: 264

Text #14

Max Range: 1.6070. Min Range: -1.6070

Max Act: 1.1366. Min Act: -0.0000

Data Index: 1098010 (C4 (Web Text))

Max Activating Token Index: 340

Text #15

Max Range: 1.6070. Min Range: -1.6070

Max Act: 1.1130. Min Act: -0.0000

Data Index: 139112 (C4 (Web Text))

Max Activating Token Index: 686

Text #16

Max Range: 1.6070. Min Range: -1.6070

Max Act: 1.0214. Min Act: -0.0000

Data Index: 776004 (C4 (Web Text))

Max Activating Token Index: 174

Text #17

Max Range: 1.6070. Min Range: -1.6070

Max Act: 1.0444. Min Act: -0.0000

Data Index: 1026222 (C4 (Web Text))

Max Activating Token Index: 578

Text #18

Max Range: 1.6070. Min Range: -1.6070

Max Act: 1.0458. Min Act: -0.0000

Data Index: 1278036 (C4 (Web Text))

Max Activating Token Index: 392

Text #19

Max Range: 1.6070. Min Range: -1.6070

Max Act: 1.0874. Min Act: -0.0000

Data Index: 222099 (C4 (Web Text))

Max Activating Token Index: 165