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

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

Neuron 810 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: 0.0520. Min Range: -0.0520

Max Act: 0.0520. Min Act: -0.0002

Data Index: 1087277 (C4 (Web Text))

Max Activating Token Index: 559

Text #1

Max Range: 0.0520. Min Range: -0.0520

Max Act: 0.0514. Min Act: -0.0002

Data Index: 420170 (C4 (Web Text))

Max Activating Token Index: 223

Text #2

Max Range: 0.0520. Min Range: -0.0520

Max Act: 0.0514. Min Act: -0.0003

Data Index: 602422 (C4 (Web Text))

Max Activating Token Index: 826

Text #3

Max Range: 0.0520. Min Range: -0.0520

Max Act: 0.0503. Min Act: -0.0003

Data Index: 862991 (C4 (Web Text))

Max Activating Token Index: 918

Text #4

Max Range: 0.0520. Min Range: -0.0520

Max Act: 0.0512. Min Act: -0.0003

Data Index: 811280 (C4 (Web Text))

Max Activating Token Index: 30

Text #5

Max Range: 0.0520. Min Range: -0.0520

Max Act: 0.0504. Min Act: -0.0003

Data Index: 853211 (C4 (Web Text))

Max Activating Token Index: 522

Text #6

Max Range: 0.0520. Min Range: -0.0520

Max Act: 0.0501. Min Act: -0.0002

Data Index: 1155999 (C4 (Web Text))

Max Activating Token Index: 204

Text #7

Max Range: 0.0520. Min Range: -0.0520

Max Act: 0.0494. Min Act: -0.0003

Data Index: 932481 (C4 (Web Text))

Max Activating Token Index: 967

Text #8

Max Range: 0.0520. Min Range: -0.0520

Max Act: 0.0483. Min Act: -0.0003

Data Index: 509871 (C4 (Web Text))

Max Activating Token Index: 101

Text #9

Max Range: 0.0520. Min Range: -0.0520

Max Act: 0.0486. Min Act: -0.0002

Data Index: 708034 (C4 (Web Text))

Max Activating Token Index: 903

Text #10

Max Range: 0.0520. Min Range: -0.0520

Max Act: 0.0491. Min Act: -0.0003

Data Index: 1056994 (C4 (Web Text))

Max Activating Token Index: 348

Text #11

Max Range: 0.0520. Min Range: -0.0520

Max Act: 0.0495. Min Act: -0.0003

Data Index: 573667 (C4 (Web Text))

Max Activating Token Index: 903

Text #12

Max Range: 0.0520. Min Range: -0.0520

Max Act: 0.0487. Min Act: -0.0003

Data Index: 1179286 (C4 (Web Text))

Max Activating Token Index: 94

Text #13

Max Range: 0.0520. Min Range: -0.0520

Max Act: 0.0486. Min Act: -0.0003

Data Index: 1066026 (C4 (Web Text))

Max Activating Token Index: 339

Text #14

Max Range: 0.0520. Min Range: -0.0520

Max Act: 0.0480. Min Act: -0.0004

Data Index: 670435 (C4 (Web Text))

Max Activating Token Index: 653

Text #15

Max Range: 0.0520. Min Range: -0.0520

Max Act: 0.0486. Min Act: -0.0004

Data Index: 811866 (C4 (Web Text))

Max Activating Token Index: 637

Text #16

Max Range: 0.0520. Min Range: -0.0520

Max Act: 0.0483. Min Act: -0.0003

Data Index: 533496 (C4 (Web Text))

Max Activating Token Index: 565

Text #17

Max Range: 0.0520. Min Range: -0.0520

Max Act: 0.0462. Min Act: -0.0004

Data Index: 536847 (C4 (Web Text))

Max Activating Token Index: 62

Text #18

Max Range: 0.0520. Min Range: -0.0520

Max Act: 0.0477. Min Act: -0.0003

Data Index: 187777 (C4 (Web Text))

Max Activating Token Index: 880

Text #19

Max Range: 0.0520. Min Range: -0.0520

Max Act: 0.0471. Min Act: -0.0002

Data Index: 148836 (C4 (Web Text))

Max Activating Token Index: 562