Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 284 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1345. Min Range: -0.1345

Max Act: 0.1345. Min Act: -0.0000

Data Index: 417892 (C4 (Web Text))

Max Activating Token Index: 723

Text #1

Max Range: 0.1345. Min Range: -0.1345

Max Act: 0.1138. Min Act: -0.0001

Data Index: 423831 (C4 (Web Text))

Max Activating Token Index: 859

Text #2

Max Range: 0.1345. Min Range: -0.1345

Max Act: 0.1079. Min Act: -0.0001

Data Index: 707805 (C4 (Web Text))

Max Activating Token Index: 96

Text #3

Max Range: 0.1345. Min Range: -0.1345

Max Act: 0.0941. Min Act: -0.0001

Data Index: 580439 (C4 (Web Text))

Max Activating Token Index: 546

Text #4

Max Range: 0.1345. Min Range: -0.1345

Max Act: 0.0943. Min Act: -0.0001

Data Index: 135926 (C4 (Web Text))

Max Activating Token Index: 499

Text #5

Max Range: 0.1345. Min Range: -0.1345

Max Act: 0.0959. Min Act: -0.0001

Data Index: 240404 (C4 (Web Text))

Max Activating Token Index: 947

Text #6

Max Range: 0.1345. Min Range: -0.1345

Max Act: 0.0939. Min Act: -0.0001

Data Index: 1335765 (C4 (Web Text))

Max Activating Token Index: 363

Text #7

Max Range: 0.1345. Min Range: -0.1345

Max Act: 0.0931. Min Act: -0.0000

Data Index: 163883 (C4 (Web Text))

Max Activating Token Index: 384

Text #8

Max Range: 0.1345. Min Range: -0.1345

Max Act: 0.0961. Min Act: -0.0001

Data Index: 978424 (C4 (Web Text))

Max Activating Token Index: 1014

Text #9

Max Range: 0.1345. Min Range: -0.1345

Max Act: 0.0962. Min Act: -0.0001

Data Index: 239076 (C4 (Web Text))

Max Activating Token Index: 164

Text #10

Max Range: 0.1345. Min Range: -0.1345

Max Act: 0.0867. Min Act: -0.0000

Data Index: 601843 (C4 (Web Text))

Max Activating Token Index: 927

Text #11

Max Range: 0.1345. Min Range: -0.1345

Max Act: 0.0887. Min Act: -0.0001

Data Index: 1278970 (C4 (Web Text))

Max Activating Token Index: 1018

Text #12

Max Range: 0.1345. Min Range: -0.1345

Max Act: 0.0919. Min Act: -0.0001

Data Index: 1208014 (C4 (Web Text))

Max Activating Token Index: 386

Text #13

Max Range: 0.1345. Min Range: -0.1345

Max Act: 0.0849. Min Act: -0.0001

Data Index: 962155 (C4 (Web Text))

Max Activating Token Index: 374

Text #14

Max Range: 0.1345. Min Range: -0.1345

Max Act: 0.0879. Min Act: -0.0001

Data Index: 1356485 (C4 (Web Text))

Max Activating Token Index: 45

Text #15

Max Range: 0.1345. Min Range: -0.1345

Max Act: 0.0868. Min Act: -0.0001

Data Index: 588673 (C4 (Web Text))

Max Activating Token Index: 41

Text #16

Max Range: 0.1345. Min Range: -0.1345

Max Act: 0.0827. Min Act: -0.0000

Data Index: 874125 (C4 (Web Text))

Max Activating Token Index: 482

Text #17

Max Range: 0.1345. Min Range: -0.1345

Max Act: 0.0789. Min Act: -0.0001

Data Index: 641594 (C4 (Web Text))

Max Activating Token Index: 757

Text #18

Max Range: 0.1345. Min Range: -0.1345

Max Act: 0.0846. Min Act: -0.0000

Data Index: 168162 (C4 (Web Text))

Max Activating Token Index: 329

Text #19

Max Range: 0.1345. Min Range: -0.1345

Max Act: 0.0823. Min Act: -0.0001

Data Index: 1258516 (C4 (Web Text))

Max Activating Token Index: 155