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

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

Neuron 699 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: 1.1264. Min Range: -1.1264

Max Act: 1.1264. Min Act: -0.0000

Data Index: 889086 (C4 (Web Text))

Max Activating Token Index: 65

Text #1

Max Range: 1.1264. Min Range: -1.1264

Max Act: 0.9870. Min Act: -0.0000

Data Index: 592475 (C4 (Web Text))

Max Activating Token Index: 614

Text #2

Max Range: 1.1264. Min Range: -1.1264

Max Act: 0.8141. Min Act: -0.0000

Data Index: 1039666 (C4 (Web Text))

Max Activating Token Index: 895

Text #3

Max Range: 1.1264. Min Range: -1.1264

Max Act: 0.8095. Min Act: -0.0000

Data Index: 685 (C4 (Web Text))

Max Activating Token Index: 430

Text #4

Max Range: 1.1264. Min Range: -1.1264

Max Act: 0.8285. Min Act: -0.0000

Data Index: 514312 (C4 (Web Text))

Max Activating Token Index: 817

Text #5

Max Range: 1.1264. Min Range: -1.1264

Max Act: 0.8249. Min Act: -0.0000

Data Index: 1168933 (C4 (Web Text))

Max Activating Token Index: 892

Text #6

Max Range: 1.1264. Min Range: -1.1264

Max Act: 0.8900. Min Act: -0.0000

Data Index: 247138 (C4 (Web Text))

Max Activating Token Index: 114

Text #7

Max Range: 1.1264. Min Range: -1.1264

Max Act: 0.8174. Min Act: -0.0000

Data Index: 1066114 (C4 (Web Text))

Max Activating Token Index: 995

Text #8

Max Range: 1.1264. Min Range: -1.1264

Max Act: 0.7628. Min Act: -0.0000

Data Index: 1320431 (C4 (Web Text))

Max Activating Token Index: 1021

Text #9

Max Range: 1.1264. Min Range: -1.1264

Max Act: 0.7813. Min Act: -0.0000

Data Index: 604117 (C4 (Web Text))

Max Activating Token Index: 514

Text #10

Max Range: 1.1264. Min Range: -1.1264

Max Act: 0.7543. Min Act: -0.0000

Data Index: 1015102 (C4 (Web Text))

Max Activating Token Index: 935

Text #11

Max Range: 1.1264. Min Range: -1.1264

Max Act: 0.7762. Min Act: -0.0000

Data Index: 1198324 (C4 (Web Text))

Max Activating Token Index: 967

Text #12

Max Range: 1.1264. Min Range: -1.1264

Max Act: 0.7692. Min Act: -0.0000

Data Index: 1117984 (C4 (Web Text))

Max Activating Token Index: 738

Text #13

Max Range: 1.1264. Min Range: -1.1264

Max Act: 0.7623. Min Act: -0.0000

Data Index: 786388 (C4 (Web Text))

Max Activating Token Index: 1019

Text #14

Max Range: 1.1264. Min Range: -1.1264

Max Act: 0.7433. Min Act: -0.0000

Data Index: 1046127 (C4 (Web Text))

Max Activating Token Index: 516

Text #15

Max Range: 1.1264. Min Range: -1.1264

Max Act: 0.6903. Min Act: -0.0000

Data Index: 653057 (C4 (Web Text))

Max Activating Token Index: 1010

Text #16

Max Range: 1.1264. Min Range: -1.1264

Max Act: 0.7260. Min Act: -0.0000

Data Index: 471466 (C4 (Web Text))

Max Activating Token Index: 143

Text #17

Max Range: 1.1264. Min Range: -1.1264

Max Act: 0.7474. Min Act: -0.0000

Data Index: 581560 (C4 (Web Text))

Max Activating Token Index: 808

Text #18

Max Range: 1.1264. Min Range: -1.1264

Max Act: 0.7273. Min Act: -0.0000

Data Index: 1367496 (Python Code)

Max Activating Token Index: 567

Text #19

Max Range: 1.1264. Min Range: -1.1264

Max Act: 0.6974. Min Act: -0.0000

Data Index: 51836 (C4 (Web Text))

Max Activating Token Index: 813