Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1447 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0530. Min Range: -0.0530

Max Act: 0.0500. Min Act: -0.0003

Data Index: 570393 (C4 (Web Text))

Max Activating Token Index: 966

Text #1

Max Range: 0.0530. Min Range: -0.0530

Max Act: 0.0530. Min Act: -0.0003

Data Index: 825552 (C4 (Web Text))

Max Activating Token Index: 587

Text #2

Max Range: 0.0530. Min Range: -0.0530

Max Act: 0.0498. Min Act: -0.0003

Data Index: 548385 (C4 (Web Text))

Max Activating Token Index: 927

Text #3

Max Range: 0.0530. Min Range: -0.0530

Max Act: 0.0479. Min Act: -0.0002

Data Index: 918270 (C4 (Web Text))

Max Activating Token Index: 405

Text #4

Max Range: 0.0530. Min Range: -0.0530

Max Act: 0.0475. Min Act: -0.0003

Data Index: 1339469 (C4 (Web Text))

Max Activating Token Index: 178

Text #5

Max Range: 0.0530. Min Range: -0.0530

Max Act: 0.0474. Min Act: -0.0003

Data Index: 662249 (C4 (Web Text))

Max Activating Token Index: 255

Text #6

Max Range: 0.0530. Min Range: -0.0530

Max Act: 0.0477. Min Act: -0.0003

Data Index: 1183700 (C4 (Web Text))

Max Activating Token Index: 579

Text #7

Max Range: 0.0530. Min Range: -0.0530

Max Act: 0.0476. Min Act: -0.0003

Data Index: 140542 (C4 (Web Text))

Max Activating Token Index: 978

Text #8

Max Range: 0.0530. Min Range: -0.0530

Max Act: 0.0503. Min Act: -0.0003

Data Index: 44861 (C4 (Web Text))

Max Activating Token Index: 931

Text #9

Max Range: 0.0530. Min Range: -0.0530

Max Act: 0.0465. Min Act: -0.0003

Data Index: 825022 (C4 (Web Text))

Max Activating Token Index: 255

Text #10

Max Range: 0.0530. Min Range: -0.0530

Max Act: 0.0457. Min Act: -0.0003

Data Index: 376444 (C4 (Web Text))

Max Activating Token Index: 915

Text #11

Max Range: 0.0530. Min Range: -0.0530

Max Act: 0.0452. Min Act: -0.0004

Data Index: 177085 (C4 (Web Text))

Max Activating Token Index: 244

Text #12

Max Range: 0.0530. Min Range: -0.0530

Max Act: 0.0432. Min Act: -0.0002

Data Index: 722418 (C4 (Web Text))

Max Activating Token Index: 455

Text #13

Max Range: 0.0530. Min Range: -0.0530

Max Act: 0.0431. Min Act: -0.0003

Data Index: 575291 (C4 (Web Text))

Max Activating Token Index: 844

Text #14

Max Range: 0.0530. Min Range: -0.0530

Max Act: 0.0459. Min Act: -0.0003

Data Index: 1340927 (C4 (Web Text))

Max Activating Token Index: 673

Text #15

Max Range: 0.0530. Min Range: -0.0530

Max Act: 0.0441. Min Act: -0.0003

Data Index: 973003 (C4 (Web Text))

Max Activating Token Index: 646

Text #16

Max Range: 0.0530. Min Range: -0.0530

Max Act: 0.0438. Min Act: -0.0003

Data Index: 1074298 (C4 (Web Text))

Max Activating Token Index: 189

Text #17

Max Range: 0.0530. Min Range: -0.0530

Max Act: 0.0452. Min Act: -0.0003

Data Index: 73831 (C4 (Web Text))

Max Activating Token Index: 448

Text #18

Max Range: 0.0530. Min Range: -0.0530

Max Act: 0.0434. Min Act: -0.0003

Data Index: 131093 (C4 (Web Text))

Max Activating Token Index: 678

Text #19

Max Range: 0.0530. Min Range: -0.0530

Max Act: 0.0442. Min Act: -0.0003

Data Index: 1160075 (C4 (Web Text))

Max Activating Token Index: 52