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

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

Neuron 954 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: 0.6404. Min Range: -0.6404

Max Act: 0.6404. Min Act: -0.0000

Data Index: 1322387 (C4 (Web Text))

Max Activating Token Index: 966

Text #1

Max Range: 0.6404. Min Range: -0.6404

Max Act: 0.5590. Min Act: -0.0000

Data Index: 489783 (C4 (Web Text))

Max Activating Token Index: 795

Text #2

Max Range: 0.6404. Min Range: -0.6404

Max Act: 0.5636. Min Act: -0.0000

Data Index: 683837 (C4 (Web Text))

Max Activating Token Index: 651

Text #3

Max Range: 0.6404. Min Range: -0.6404

Max Act: 0.5301. Min Act: -0.0000

Data Index: 469041 (C4 (Web Text))

Max Activating Token Index: 525

Text #4

Max Range: 0.6404. Min Range: -0.6404

Max Act: 0.5587. Min Act: -0.0000

Data Index: 340788 (C4 (Web Text))

Max Activating Token Index: 691

Text #5

Max Range: 0.6404. Min Range: -0.6404

Max Act: 0.5401. Min Act: -0.0000

Data Index: 698840 (C4 (Web Text))

Max Activating Token Index: 69

Text #6

Max Range: 0.6404. Min Range: -0.6404

Max Act: 0.5105. Min Act: -0.0000

Data Index: 1349958 (C4 (Web Text))

Max Activating Token Index: 315

Text #7

Max Range: 0.6404. Min Range: -0.6404

Max Act: 0.5078. Min Act: -0.0000

Data Index: 88391 (C4 (Web Text))

Max Activating Token Index: 316

Text #8

Max Range: 0.6404. Min Range: -0.6404

Max Act: 0.4970. Min Act: -0.0000

Data Index: 513486 (C4 (Web Text))

Max Activating Token Index: 689

Text #9

Max Range: 0.6404. Min Range: -0.6404

Max Act: 0.5360. Min Act: -0.0000

Data Index: 1318980 (C4 (Web Text))

Max Activating Token Index: 717

Text #10

Max Range: 0.6404. Min Range: -0.6404

Max Act: 0.4802. Min Act: -0.0000

Data Index: 133251 (C4 (Web Text))

Max Activating Token Index: 729

Text #11

Max Range: 0.6404. Min Range: -0.6404

Max Act: 0.4842. Min Act: -0.0000

Data Index: 312831 (C4 (Web Text))

Max Activating Token Index: 569

Text #12

Max Range: 0.6404. Min Range: -0.6404

Max Act: 0.4965. Min Act: -0.0000

Data Index: 569426 (C4 (Web Text))

Max Activating Token Index: 584

Text #13

Max Range: 0.6404. Min Range: -0.6404

Max Act: 0.4917. Min Act: -0.0000

Data Index: 922018 (C4 (Web Text))

Max Activating Token Index: 520

Text #14

Max Range: 0.6404. Min Range: -0.6404

Max Act: 0.4582. Min Act: -0.0000

Data Index: 906286 (C4 (Web Text))

Max Activating Token Index: 401

Text #15

Max Range: 0.6404. Min Range: -0.6404

Max Act: 0.4548. Min Act: -0.0000

Data Index: 574481 (C4 (Web Text))

Max Activating Token Index: 250

Text #16

Max Range: 0.6404. Min Range: -0.6404

Max Act: 0.4863. Min Act: -0.0000

Data Index: 551201 (C4 (Web Text))

Max Activating Token Index: 778

Text #17

Max Range: 0.6404. Min Range: -0.6404

Max Act: 0.4681. Min Act: -0.0000

Data Index: 936069 (C4 (Web Text))

Max Activating Token Index: 633

Text #18

Max Range: 0.6404. Min Range: -0.6404

Max Act: 0.4790. Min Act: -0.0000

Data Index: 915001 (C4 (Web Text))

Max Activating Token Index: 1020

Text #19

Max Range: 0.6404. Min Range: -0.6404

Max Act: 0.4929. Min Act: -0.0000

Data Index: 1109711 (C4 (Web Text))

Max Activating Token Index: 110