Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2038 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.4269. Min Range: -0.4269

Max Act: 0.4269. Min Act: -0.0004

Data Index: 1130341 (C4 (Web Text))

Max Activating Token Index: 623

Text #1

Max Range: 0.4269. Min Range: -0.4269

Max Act: 0.3978. Min Act: -0.0004

Data Index: 45535 (C4 (Web Text))

Max Activating Token Index: 637

Text #2

Max Range: 0.4269. Min Range: -0.4269

Max Act: 0.3725. Min Act: -0.0004

Data Index: 1330323 (C4 (Web Text))

Max Activating Token Index: 540

Text #3

Max Range: 0.4269. Min Range: -0.4269

Max Act: 0.3769. Min Act: -0.0004

Data Index: 514566 (C4 (Web Text))

Max Activating Token Index: 437

Text #4

Max Range: 0.4269. Min Range: -0.4269

Max Act: 0.3778. Min Act: -0.0004

Data Index: 428403 (C4 (Web Text))

Max Activating Token Index: 212

Text #5

Max Range: 0.4269. Min Range: -0.4269

Max Act: 0.3552. Min Act: -0.0004

Data Index: 715847 (C4 (Web Text))

Max Activating Token Index: 326

Text #6

Max Range: 0.4269. Min Range: -0.4269

Max Act: 0.3625. Min Act: -0.0004

Data Index: 937992 (C4 (Web Text))

Max Activating Token Index: 184

Text #7

Max Range: 0.4269. Min Range: -0.4269

Max Act: 0.3600. Min Act: -0.0004

Data Index: 32344 (C4 (Web Text))

Max Activating Token Index: 66

Text #8

Max Range: 0.4269. Min Range: -0.4269

Max Act: 0.3652. Min Act: -0.0004

Data Index: 591057 (C4 (Web Text))

Max Activating Token Index: 287

Text #9

Max Range: 0.4269. Min Range: -0.4269

Max Act: 0.3851. Min Act: -0.0004

Data Index: 1345347 (C4 (Web Text))

Max Activating Token Index: 669

Text #10

Max Range: 0.4269. Min Range: -0.4269

Max Act: 0.3398. Min Act: -0.0004

Data Index: 165038 (C4 (Web Text))

Max Activating Token Index: 661

Text #11

Max Range: 0.4269. Min Range: -0.4269

Max Act: 0.3563. Min Act: -0.0004

Data Index: 56543 (C4 (Web Text))

Max Activating Token Index: 236

Text #12

Max Range: 0.4269. Min Range: -0.4269

Max Act: 0.3447. Min Act: -0.0004

Data Index: 281580 (C4 (Web Text))

Max Activating Token Index: 144

Text #13

Max Range: 0.4269. Min Range: -0.4269

Max Act: 0.3540. Min Act: -0.0004

Data Index: 594434 (C4 (Web Text))

Max Activating Token Index: 184

Text #14

Max Range: 0.4269. Min Range: -0.4269

Max Act: 0.3544. Min Act: -0.0004

Data Index: 930712 (C4 (Web Text))

Max Activating Token Index: 437

Text #15

Max Range: 0.4269. Min Range: -0.4269

Max Act: 0.3617. Min Act: -0.0004

Data Index: 445466 (C4 (Web Text))

Max Activating Token Index: 538

Text #16

Max Range: 0.4269. Min Range: -0.4269

Max Act: 0.3517. Min Act: -0.0004

Data Index: 778927 (C4 (Web Text))

Max Activating Token Index: 888

Text #17

Max Range: 0.4269. Min Range: -0.4269

Max Act: 0.3486. Min Act: -0.0004

Data Index: 304725 (C4 (Web Text))

Max Activating Token Index: 388

Text #18

Max Range: 0.4269. Min Range: -0.4269

Max Act: 0.3638. Min Act: -0.0004

Data Index: 1127080 (C4 (Web Text))

Max Activating Token Index: 73

Text #19

Max Range: 0.4269. Min Range: -0.4269

Max Act: 0.3553. Min Act: -0.0004

Data Index: 924619 (C4 (Web Text))

Max Activating Token Index: 363