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

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

Neuron 4915 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: 0.0537. Min Range: -0.0537

Max Act: 0.0531. Min Act: -0.0002

Data Index: 1273034 (C4 (Web Text))

Max Activating Token Index: 72

Text #1

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0537. Min Act: -0.0002

Data Index: 246154 (C4 (Web Text))

Max Activating Token Index: 191

Text #2

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0518. Min Act: -0.0002

Data Index: 1093260 (C4 (Web Text))

Max Activating Token Index: 95

Text #3

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0507. Min Act: -0.0002

Data Index: 392609 (C4 (Web Text))

Max Activating Token Index: 775

Text #4

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0483. Min Act: -0.0002

Data Index: 811252 (C4 (Web Text))

Max Activating Token Index: 772

Text #5

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0481. Min Act: -0.0002

Data Index: 201680 (C4 (Web Text))

Max Activating Token Index: 631

Text #6

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0495. Min Act: -0.0002

Data Index: 1068711 (C4 (Web Text))

Max Activating Token Index: 430

Text #7

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0481. Min Act: -0.0002

Data Index: 661741 (C4 (Web Text))

Max Activating Token Index: 71

Text #8

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0473. Min Act: -0.0002

Data Index: 614225 (C4 (Web Text))

Max Activating Token Index: 379

Text #9

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0454. Min Act: -0.0002

Data Index: 980028 (C4 (Web Text))

Max Activating Token Index: 284

Text #10

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0468. Min Act: -0.0002

Data Index: 542513 (C4 (Web Text))

Max Activating Token Index: 1000

Text #11

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0486. Min Act: -0.0002

Data Index: 578709 (C4 (Web Text))

Max Activating Token Index: 694

Text #12

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0453. Min Act: -0.0002

Data Index: 1023248 (C4 (Web Text))

Max Activating Token Index: 291

Text #13

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0463. Min Act: -0.0002

Data Index: 514357 (C4 (Web Text))

Max Activating Token Index: 527

Text #14

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0467. Min Act: -0.0002

Data Index: 870790 (C4 (Web Text))

Max Activating Token Index: 327

Text #15

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0476. Min Act: -0.0002

Data Index: 774365 (C4 (Web Text))

Max Activating Token Index: 191

Text #16

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0448. Min Act: -0.0002

Data Index: 562307 (C4 (Web Text))

Max Activating Token Index: 872

Text #17

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0452. Min Act: -0.0002

Data Index: 791051 (C4 (Web Text))

Max Activating Token Index: 860

Text #18

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0465. Min Act: -0.0002

Data Index: 554959 (C4 (Web Text))

Max Activating Token Index: 453

Text #19

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0446. Min Act: -0.0002

Data Index: 486712 (C4 (Web Text))

Max Activating Token Index: 741