Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5152 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0558. Min Act: -0.0002

Data Index: 391830 (C4 (Web Text))

Max Activating Token Index: 494

Text #1

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0553. Min Act: -0.0002

Data Index: 9823 (C4 (Web Text))

Max Activating Token Index: 512

Text #2

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0547. Min Act: -0.0002

Data Index: 1305761 (C4 (Web Text))

Max Activating Token Index: 242

Text #3

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0547. Min Act: -0.0002

Data Index: 903248 (C4 (Web Text))

Max Activating Token Index: 544

Text #4

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0537. Min Act: -0.0002

Data Index: 520099 (C4 (Web Text))

Max Activating Token Index: 273

Text #5

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0528. Min Act: -0.0002

Data Index: 286398 (C4 (Web Text))

Max Activating Token Index: 617

Text #6

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0536. Min Act: -0.0002

Data Index: 626703 (C4 (Web Text))

Max Activating Token Index: 293

Text #7

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0517. Min Act: -0.0002

Data Index: 1218224 (C4 (Web Text))

Max Activating Token Index: 204

Text #8

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0490. Min Act: -0.0002

Data Index: 133832 (C4 (Web Text))

Max Activating Token Index: 858

Text #9

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0492. Min Act: -0.0002

Data Index: 295485 (C4 (Web Text))

Max Activating Token Index: 277

Text #10

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0500. Min Act: -0.0002

Data Index: 378478 (C4 (Web Text))

Max Activating Token Index: 861

Text #11

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0500. Min Act: -0.0002

Data Index: 1350118 (C4 (Web Text))

Max Activating Token Index: 936

Text #12

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0497. Min Act: -0.0002

Data Index: 1276802 (C4 (Web Text))

Max Activating Token Index: 848

Text #13

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0530. Min Act: -0.0002

Data Index: 819111 (C4 (Web Text))

Max Activating Token Index: 959

Text #14

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0491. Min Act: -0.0002

Data Index: 628829 (C4 (Web Text))

Max Activating Token Index: 717

Text #15

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0464. Min Act: -0.0002

Data Index: 1529471 (Python Code)

Max Activating Token Index: 159

Text #16

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0471. Min Act: -0.0002

Data Index: 153900 (C4 (Web Text))

Max Activating Token Index: 1021

Text #17

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0470. Min Act: -0.0002

Data Index: 774714 (C4 (Web Text))

Max Activating Token Index: 84

Text #18

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0461. Min Act: -0.0002

Data Index: 1474418 (Python Code)

Max Activating Token Index: 90

Text #19

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0456. Min Act: -0.0002

Data Index: 99356 (C4 (Web Text))

Max Activating Token Index: 445