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

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

Neuron 2543 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: 0.0590. Min Range: -0.0590

Max Act: 0.0590. Min Act: -0.0003

Data Index: 1207552 (C4 (Web Text))

Max Activating Token Index: 270

Text #1

Max Range: 0.0590. Min Range: -0.0590

Max Act: 0.0585. Min Act: -0.0003

Data Index: 382145 (C4 (Web Text))

Max Activating Token Index: 49

Text #2

Max Range: 0.0590. Min Range: -0.0590

Max Act: 0.0574. Min Act: -0.0002

Data Index: 1141894 (C4 (Web Text))

Max Activating Token Index: 59

Text #3

Max Range: 0.0590. Min Range: -0.0590

Max Act: 0.0537. Min Act: -0.0003

Data Index: 832911 (C4 (Web Text))

Max Activating Token Index: 402

Text #4

Max Range: 0.0590. Min Range: -0.0590

Max Act: 0.0525. Min Act: -0.0003

Data Index: 286200 (C4 (Web Text))

Max Activating Token Index: 526

Text #5

Max Range: 0.0590. Min Range: -0.0590

Max Act: 0.0546. Min Act: -0.0002

Data Index: 904029 (C4 (Web Text))

Max Activating Token Index: 947

Text #6

Max Range: 0.0590. Min Range: -0.0590

Max Act: 0.0490. Min Act: -0.0003

Data Index: 521339 (C4 (Web Text))

Max Activating Token Index: 587

Text #7

Max Range: 0.0590. Min Range: -0.0590

Max Act: 0.0474. Min Act: -0.0003

Data Index: 729918 (C4 (Web Text))

Max Activating Token Index: 630

Text #8

Max Range: 0.0590. Min Range: -0.0590

Max Act: 0.0467. Min Act: -0.0003

Data Index: 171509 (C4 (Web Text))

Max Activating Token Index: 801

Text #9

Max Range: 0.0590. Min Range: -0.0590

Max Act: 0.0467. Min Act: -0.0003

Data Index: 1062047 (C4 (Web Text))

Max Activating Token Index: 303

Text #10

Max Range: 0.0590. Min Range: -0.0590

Max Act: 0.0450. Min Act: -0.0003

Data Index: 394364 (C4 (Web Text))

Max Activating Token Index: 263

Text #11

Max Range: 0.0590. Min Range: -0.0590

Max Act: 0.0429. Min Act: -0.0003

Data Index: 27292 (C4 (Web Text))

Max Activating Token Index: 285

Text #12

Max Range: 0.0590. Min Range: -0.0590

Max Act: 0.0433. Min Act: -0.0003

Data Index: 996980 (C4 (Web Text))

Max Activating Token Index: 118

Text #13

Max Range: 0.0590. Min Range: -0.0590

Max Act: 0.0408. Min Act: -0.0003

Data Index: 1112008 (C4 (Web Text))

Max Activating Token Index: 380

Text #14

Max Range: 0.0590. Min Range: -0.0590

Max Act: 0.0408. Min Act: -0.0003

Data Index: 1255406 (C4 (Web Text))

Max Activating Token Index: 33

Text #15

Max Range: 0.0590. Min Range: -0.0590

Max Act: 0.0408. Min Act: -0.0003

Data Index: 1121937 (C4 (Web Text))

Max Activating Token Index: 366

Text #16

Max Range: 0.0590. Min Range: -0.0590

Max Act: 0.0398. Min Act: -0.0003

Data Index: 196970 (C4 (Web Text))

Max Activating Token Index: 176

Text #17

Max Range: 0.0590. Min Range: -0.0590

Max Act: 0.0421. Min Act: -0.0003

Data Index: 20642 (C4 (Web Text))

Max Activating Token Index: 418

Text #18

Max Range: 0.0590. Min Range: -0.0590

Max Act: 0.0406. Min Act: -0.0003

Data Index: 1072555 (C4 (Web Text))

Max Activating Token Index: 151

Text #19

Max Range: 0.0590. Min Range: -0.0590

Max Act: 0.0401. Min Act: -0.0003

Data Index: 808683 (C4 (Web Text))

Max Activating Token Index: 13