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

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

Neuron 1987 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6032. Min Range: -0.6032

Max Act: 0.6032. Min Act: -0.0001

Data Index: 632630 (C4 (Web Text))

Max Activating Token Index: 242

Text #1

Max Range: 0.6032. Min Range: -0.6032

Max Act: 0.5022. Min Act: -0.0001

Data Index: 833709 (C4 (Web Text))

Max Activating Token Index: 653

Text #2

Max Range: 0.6032. Min Range: -0.6032

Max Act: 0.5334. Min Act: -0.0001

Data Index: 9490 (C4 (Web Text))

Max Activating Token Index: 435

Text #3

Max Range: 0.6032. Min Range: -0.6032

Max Act: 0.4624. Min Act: -0.0001

Data Index: 807478 (C4 (Web Text))

Max Activating Token Index: 556

Text #4

Max Range: 0.6032. Min Range: -0.6032

Max Act: 0.4690. Min Act: -0.0001

Data Index: 966188 (C4 (Web Text))

Max Activating Token Index: 723

Text #5

Max Range: 0.6032. Min Range: -0.6032

Max Act: 0.4372. Min Act: -0.0001

Data Index: 1086501 (C4 (Web Text))

Max Activating Token Index: 159

Text #6

Max Range: 0.6032. Min Range: -0.6032

Max Act: 0.4535. Min Act: -0.0001

Data Index: 1213523 (C4 (Web Text))

Max Activating Token Index: 378

Text #7

Max Range: 0.6032. Min Range: -0.6032

Max Act: 0.4528. Min Act: -0.0001

Data Index: 343657 (C4 (Web Text))

Max Activating Token Index: 897

Text #8

Max Range: 0.6032. Min Range: -0.6032

Max Act: 0.4531. Min Act: -0.0001

Data Index: 811116 (C4 (Web Text))

Max Activating Token Index: 683

Text #9

Max Range: 0.6032. Min Range: -0.6032

Max Act: 0.4708. Min Act: -0.0001

Data Index: 872686 (C4 (Web Text))

Max Activating Token Index: 631

Text #10

Max Range: 0.6032. Min Range: -0.6032

Max Act: 0.4323. Min Act: -0.0001

Data Index: 541904 (C4 (Web Text))

Max Activating Token Index: 621

Text #11

Max Range: 0.6032. Min Range: -0.6032

Max Act: 0.4592. Min Act: -0.0001

Data Index: 635668 (C4 (Web Text))

Max Activating Token Index: 441

Text #12

Max Range: 0.6032. Min Range: -0.6032

Max Act: 0.4326. Min Act: -0.0001

Data Index: 20910 (C4 (Web Text))

Max Activating Token Index: 536

Text #13

Max Range: 0.6032. Min Range: -0.6032

Max Act: 0.4101. Min Act: -0.0001

Data Index: 207496 (C4 (Web Text))

Max Activating Token Index: 818

Text #14

Max Range: 0.6032. Min Range: -0.6032

Max Act: 0.4633. Min Act: -0.0001

Data Index: 915574 (C4 (Web Text))

Max Activating Token Index: 397

Text #15

Max Range: 0.6032. Min Range: -0.6032

Max Act: 0.4037. Min Act: -0.0001

Data Index: 808317 (C4 (Web Text))

Max Activating Token Index: 478

Text #16

Max Range: 0.6032. Min Range: -0.6032

Max Act: 0.4286. Min Act: -0.0001

Data Index: 371723 (C4 (Web Text))

Max Activating Token Index: 114

Text #17

Max Range: 0.6032. Min Range: -0.6032

Max Act: 0.4275. Min Act: -0.0001

Data Index: 741976 (C4 (Web Text))

Max Activating Token Index: 127

Text #18

Max Range: 0.6032. Min Range: -0.6032

Max Act: 0.4212. Min Act: -0.0001

Data Index: 845341 (C4 (Web Text))

Max Activating Token Index: 77

Text #19

Max Range: 0.6032. Min Range: -0.6032

Max Act: 0.4332. Min Act: -0.0001

Data Index: 315126 (C4 (Web Text))

Max Activating Token Index: 899