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

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

Neuron 2912 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1754. Min Range: -0.1754

Max Act: 0.1754. Min Act: -0.0001

Data Index: 698768 (C4 (Web Text))

Max Activating Token Index: 932

Text #1

Max Range: 0.1754. Min Range: -0.1754

Max Act: 0.1362. Min Act: -0.0001

Data Index: 426515 (C4 (Web Text))

Max Activating Token Index: 524

Text #2

Max Range: 0.1754. Min Range: -0.1754

Max Act: 0.1249. Min Act: -0.0001

Data Index: 81125 (C4 (Web Text))

Max Activating Token Index: 201

Text #3

Max Range: 0.1754. Min Range: -0.1754

Max Act: 0.1380. Min Act: -0.0001

Data Index: 683716 (C4 (Web Text))

Max Activating Token Index: 887

Text #4

Max Range: 0.1754. Min Range: -0.1754

Max Act: 0.1308. Min Act: -0.0001

Data Index: 68276 (C4 (Web Text))

Max Activating Token Index: 329

Text #5

Max Range: 0.1754. Min Range: -0.1754

Max Act: 0.1309. Min Act: -0.0001

Data Index: 788875 (C4 (Web Text))

Max Activating Token Index: 397

Text #6

Max Range: 0.1754. Min Range: -0.1754

Max Act: 0.1256. Min Act: -0.0001

Data Index: 267205 (C4 (Web Text))

Max Activating Token Index: 806

Text #7

Max Range: 0.1754. Min Range: -0.1754

Max Act: 0.1285. Min Act: -0.0001

Data Index: 260171 (C4 (Web Text))

Max Activating Token Index: 1008

Text #8

Max Range: 0.1754. Min Range: -0.1754

Max Act: 0.1090. Min Act: -0.0001

Data Index: 643357 (C4 (Web Text))

Max Activating Token Index: 528

Text #9

Max Range: 0.1754. Min Range: -0.1754

Max Act: 0.1084. Min Act: -0.0001

Data Index: 21107 (C4 (Web Text))

Max Activating Token Index: 129

Text #10

Max Range: 0.1754. Min Range: -0.1754

Max Act: 0.1038. Min Act: -0.0001

Data Index: 982475 (C4 (Web Text))

Max Activating Token Index: 423

Text #11

Max Range: 0.1754. Min Range: -0.1754

Max Act: 0.1100. Min Act: -0.0001

Data Index: 522449 (C4 (Web Text))

Max Activating Token Index: 480

Text #12

Max Range: 0.1754. Min Range: -0.1754

Max Act: 0.1123. Min Act: -0.0001

Data Index: 957843 (C4 (Web Text))

Max Activating Token Index: 619

Text #13

Max Range: 0.1754. Min Range: -0.1754

Max Act: 0.0989. Min Act: -0.0001

Data Index: 460976 (C4 (Web Text))

Max Activating Token Index: 746

Text #14

Max Range: 0.1754. Min Range: -0.1754

Max Act: 0.1173. Min Act: -0.0001

Data Index: 769730 (C4 (Web Text))

Max Activating Token Index: 927

Text #15

Max Range: 0.1754. Min Range: -0.1754

Max Act: 0.1128. Min Act: -0.0001

Data Index: 1264982 (C4 (Web Text))

Max Activating Token Index: 1014

Text #16

Max Range: 0.1754. Min Range: -0.1754

Max Act: 0.1087. Min Act: -0.0001

Data Index: 1249088 (C4 (Web Text))

Max Activating Token Index: 473

Text #17

Max Range: 0.1754. Min Range: -0.1754

Max Act: 0.0977. Min Act: -0.0001

Data Index: 427875 (C4 (Web Text))

Max Activating Token Index: 563

Text #18

Max Range: 0.1754. Min Range: -0.1754

Max Act: 0.1034. Min Act: -0.0001

Data Index: 682842 (C4 (Web Text))

Max Activating Token Index: 781

Text #19

Max Range: 0.1754. Min Range: -0.1754

Max Act: 0.1077. Min Act: -0.0001

Data Index: 876375 (C4 (Web Text))

Max Activating Token Index: 341