Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3977 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1954. Min Range: -0.1954

Max Act: 0.1954. Min Act: -0.0001

Data Index: 627579 (C4 (Web Text))

Max Activating Token Index: 394

Text #1

Max Range: 0.1954. Min Range: -0.1954

Max Act: 0.1640. Min Act: -0.0001

Data Index: 816428 (C4 (Web Text))

Max Activating Token Index: 631

Text #2

Max Range: 0.1954. Min Range: -0.1954

Max Act: 0.1460. Min Act: -0.0001

Data Index: 104170 (C4 (Web Text))

Max Activating Token Index: 735

Text #3

Max Range: 0.1954. Min Range: -0.1954

Max Act: 0.1452. Min Act: -0.0001

Data Index: 1112156 (C4 (Web Text))

Max Activating Token Index: 549

Text #4

Max Range: 0.1954. Min Range: -0.1954

Max Act: 0.1370. Min Act: -0.0001

Data Index: 686147 (C4 (Web Text))

Max Activating Token Index: 591

Text #5

Max Range: 0.1954. Min Range: -0.1954

Max Act: 0.1341. Min Act: -0.0001

Data Index: 716775 (C4 (Web Text))

Max Activating Token Index: 411

Text #6

Max Range: 0.1954. Min Range: -0.1954

Max Act: 0.1363. Min Act: -0.0001

Data Index: 270901 (C4 (Web Text))

Max Activating Token Index: 930

Text #7

Max Range: 0.1954. Min Range: -0.1954

Max Act: 0.1148. Min Act: -0.0001

Data Index: 328548 (C4 (Web Text))

Max Activating Token Index: 220

Text #8

Max Range: 0.1954. Min Range: -0.1954

Max Act: 0.1250. Min Act: -0.0001

Data Index: 169928 (C4 (Web Text))

Max Activating Token Index: 993

Text #9

Max Range: 0.1954. Min Range: -0.1954

Max Act: 0.1278. Min Act: -0.0001

Data Index: 226045 (C4 (Web Text))

Max Activating Token Index: 643

Text #10

Max Range: 0.1954. Min Range: -0.1954

Max Act: 0.1107. Min Act: -0.0001

Data Index: 750989 (C4 (Web Text))

Max Activating Token Index: 243

Text #11

Max Range: 0.1954. Min Range: -0.1954

Max Act: 0.1196. Min Act: -0.0001

Data Index: 1294652 (C4 (Web Text))

Max Activating Token Index: 417

Text #12

Max Range: 0.1954. Min Range: -0.1954

Max Act: 0.1040. Min Act: -0.0001

Data Index: 180083 (C4 (Web Text))

Max Activating Token Index: 502

Text #13

Max Range: 0.1954. Min Range: -0.1954

Max Act: 0.1072. Min Act: -0.0001

Data Index: 762973 (C4 (Web Text))

Max Activating Token Index: 607

Text #14

Max Range: 0.1954. Min Range: -0.1954

Max Act: 0.1031. Min Act: -0.0001

Data Index: 1197778 (C4 (Web Text))

Max Activating Token Index: 730

Text #15

Max Range: 0.1954. Min Range: -0.1954

Max Act: 0.0951. Min Act: -0.0001

Data Index: 1289078 (C4 (Web Text))

Max Activating Token Index: 265

Text #16

Max Range: 0.1954. Min Range: -0.1954

Max Act: 0.1088. Min Act: -0.0001

Data Index: 4715 (C4 (Web Text))

Max Activating Token Index: 385

Text #17

Max Range: 0.1954. Min Range: -0.1954

Max Act: 0.0968. Min Act: -0.0001

Data Index: 214684 (C4 (Web Text))

Max Activating Token Index: 364

Text #18

Max Range: 0.1954. Min Range: -0.1954

Max Act: 0.1039. Min Act: -0.0001

Data Index: 1039684 (C4 (Web Text))

Max Activating Token Index: 853

Text #19

Max Range: 0.1954. Min Range: -0.1954

Max Act: 0.0847. Min Act: -0.0001

Data Index: 817048 (C4 (Web Text))

Max Activating Token Index: 243