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

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

Neuron 909 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.6573. Min Range: -0.6573

Max Act: 0.6573. Min Act: -0.0003

Data Index: 594586 (C4 (Web Text))

Max Activating Token Index: 528

Text #1

Max Range: 0.6573. Min Range: -0.6573

Max Act: 0.6508. Min Act: -0.0003

Data Index: 614260 (C4 (Web Text))

Max Activating Token Index: 617

Text #2

Max Range: 0.6573. Min Range: -0.6573

Max Act: 0.6113. Min Act: -0.0003

Data Index: 144636 (C4 (Web Text))

Max Activating Token Index: 584

Text #3

Max Range: 0.6573. Min Range: -0.6573

Max Act: 0.5968. Min Act: -0.0003

Data Index: 1074447 (C4 (Web Text))

Max Activating Token Index: 711

Text #4

Max Range: 0.6573. Min Range: -0.6573

Max Act: 0.5895. Min Act: -0.0003

Data Index: 156554 (C4 (Web Text))

Max Activating Token Index: 474

Text #5

Max Range: 0.6573. Min Range: -0.6573

Max Act: 0.5832. Min Act: -0.0003

Data Index: 32085 (C4 (Web Text))

Max Activating Token Index: 106

Text #6

Max Range: 0.6573. Min Range: -0.6573

Max Act: 0.5539. Min Act: -0.0003

Data Index: 969340 (C4 (Web Text))

Max Activating Token Index: 300

Text #7

Max Range: 0.6573. Min Range: -0.6573

Max Act: 0.5840. Min Act: -0.0003

Data Index: 918147 (C4 (Web Text))

Max Activating Token Index: 153

Text #8

Max Range: 0.6573. Min Range: -0.6573

Max Act: 0.5676. Min Act: -0.0003

Data Index: 278678 (C4 (Web Text))

Max Activating Token Index: 746

Text #9

Max Range: 0.6573. Min Range: -0.6573

Max Act: 0.5684. Min Act: -0.0003

Data Index: 669663 (C4 (Web Text))

Max Activating Token Index: 461

Text #10

Max Range: 0.6573. Min Range: -0.6573

Max Act: 0.5303. Min Act: -0.0003

Data Index: 352768 (C4 (Web Text))

Max Activating Token Index: 104

Text #11

Max Range: 0.6573. Min Range: -0.6573

Max Act: 0.5310. Min Act: -0.0003

Data Index: 558344 (C4 (Web Text))

Max Activating Token Index: 379

Text #12

Max Range: 0.6573. Min Range: -0.6573

Max Act: 0.5233. Min Act: -0.0003

Data Index: 1153234 (C4 (Web Text))

Max Activating Token Index: 303

Text #13

Max Range: 0.6573. Min Range: -0.6573

Max Act: 0.5409. Min Act: -0.0003

Data Index: 559481 (C4 (Web Text))

Max Activating Token Index: 90

Text #14

Max Range: 0.6573. Min Range: -0.6573

Max Act: 0.5154. Min Act: -0.0003

Data Index: 1304812 (C4 (Web Text))

Max Activating Token Index: 288

Text #15

Max Range: 0.6573. Min Range: -0.6573

Max Act: 0.5321. Min Act: -0.0003

Data Index: 499460 (C4 (Web Text))

Max Activating Token Index: 158

Text #16

Max Range: 0.6573. Min Range: -0.6573

Max Act: 0.5145. Min Act: -0.0003

Data Index: 320737 (C4 (Web Text))

Max Activating Token Index: 528

Text #17

Max Range: 0.6573. Min Range: -0.6573

Max Act: 0.5119. Min Act: -0.0003

Data Index: 1234654 (C4 (Web Text))

Max Activating Token Index: 902

Text #18

Max Range: 0.6573. Min Range: -0.6573

Max Act: 0.5115. Min Act: -0.0003

Data Index: 574069 (C4 (Web Text))

Max Activating Token Index: 196

Text #19

Max Range: 0.6573. Min Range: -0.6573

Max Act: 0.4957. Min Act: -0.0003

Data Index: 42733 (C4 (Web Text))

Max Activating Token Index: 269