Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 10 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2652. Min Range: -0.2652

Max Act: 0.2538. Min Act: -0.0001

Data Index: 1138584 (C4 (Web Text))

Max Activating Token Index: 979

Text #1

Max Range: 0.2652. Min Range: -0.2652

Max Act: 0.2652. Min Act: -0.0001

Data Index: 71603 (C4 (Web Text))

Max Activating Token Index: 298

Text #2

Max Range: 0.2652. Min Range: -0.2652

Max Act: 0.2212. Min Act: -0.0001

Data Index: 319922 (C4 (Web Text))

Max Activating Token Index: 871

Text #3

Max Range: 0.2652. Min Range: -0.2652

Max Act: 0.2120. Min Act: -0.0001

Data Index: 1172212 (C4 (Web Text))

Max Activating Token Index: 492

Text #4

Max Range: 0.2652. Min Range: -0.2652

Max Act: 0.2050. Min Act: -0.0001

Data Index: 920032 (C4 (Web Text))

Max Activating Token Index: 965

Text #5

Max Range: 0.2652. Min Range: -0.2652

Max Act: 0.2262. Min Act: -0.0001

Data Index: 299984 (C4 (Web Text))

Max Activating Token Index: 696

Text #6

Max Range: 0.2652. Min Range: -0.2652

Max Act: 0.2157. Min Act: -0.0001

Data Index: 774647 (C4 (Web Text))

Max Activating Token Index: 280

Text #7

Max Range: 0.2652. Min Range: -0.2652

Max Act: 0.1973. Min Act: -0.0001

Data Index: 2817 (C4 (Web Text))

Max Activating Token Index: 29

Text #8

Max Range: 0.2652. Min Range: -0.2652

Max Act: 0.2028. Min Act: -0.0001

Data Index: 321884 (C4 (Web Text))

Max Activating Token Index: 928

Text #9

Max Range: 0.2652. Min Range: -0.2652

Max Act: 0.2019. Min Act: -0.0001

Data Index: 872396 (C4 (Web Text))

Max Activating Token Index: 537

Text #10

Max Range: 0.2652. Min Range: -0.2652

Max Act: 0.2081. Min Act: -0.0001

Data Index: 773649 (C4 (Web Text))

Max Activating Token Index: 417

Text #11

Max Range: 0.2652. Min Range: -0.2652

Max Act: 0.2000. Min Act: -0.0001

Data Index: 683398 (C4 (Web Text))

Max Activating Token Index: 843

Text #12

Max Range: 0.2652. Min Range: -0.2652

Max Act: 0.1980. Min Act: -0.0001

Data Index: 807628 (C4 (Web Text))

Max Activating Token Index: 724

Text #13

Max Range: 0.2652. Min Range: -0.2652

Max Act: 0.2096. Min Act: -0.0001

Data Index: 935024 (C4 (Web Text))

Max Activating Token Index: 368

Text #14

Max Range: 0.2652. Min Range: -0.2652

Max Act: 0.1986. Min Act: -0.0001

Data Index: 1254385 (C4 (Web Text))

Max Activating Token Index: 446

Text #15

Max Range: 0.2652. Min Range: -0.2652

Max Act: 0.1921. Min Act: -0.0001

Data Index: 755174 (C4 (Web Text))

Max Activating Token Index: 25

Text #16

Max Range: 0.2652. Min Range: -0.2652

Max Act: 0.2036. Min Act: -0.0001

Data Index: 1247828 (C4 (Web Text))

Max Activating Token Index: 289

Text #17

Max Range: 0.2652. Min Range: -0.2652

Max Act: 0.2040. Min Act: -0.0001

Data Index: 1224268 (C4 (Web Text))

Max Activating Token Index: 795

Text #18

Max Range: 0.2652. Min Range: -0.2652

Max Act: 0.1952. Min Act: -0.0001

Data Index: 256394 (C4 (Web Text))

Max Activating Token Index: 258

Text #19

Max Range: 0.2652. Min Range: -0.2652

Max Act: 0.1994. Min Act: -0.0001

Data Index: 521373 (C4 (Web Text))

Max Activating Token Index: 725