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

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

Neuron 3063 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: 0.0653. Min Range: -0.0653

Max Act: 0.0653. Min Act: -0.0002

Data Index: 18984 (C4 (Web Text))

Max Activating Token Index: 129

Text #1

Max Range: 0.0653. Min Range: -0.0653

Max Act: 0.0432. Min Act: -0.0002

Data Index: 789316 (C4 (Web Text))

Max Activating Token Index: 71

Text #2

Max Range: 0.0653. Min Range: -0.0653

Max Act: 0.0381. Min Act: -0.0002

Data Index: 590336 (C4 (Web Text))

Max Activating Token Index: 24

Text #3

Max Range: 0.0653. Min Range: -0.0653

Max Act: 0.0354. Min Act: -0.0002

Data Index: 461253 (C4 (Web Text))

Max Activating Token Index: 305

Text #4

Max Range: 0.0653. Min Range: -0.0653

Max Act: 0.0374. Min Act: -0.0002

Data Index: 452212 (C4 (Web Text))

Max Activating Token Index: 488

Text #5

Max Range: 0.0653. Min Range: -0.0653

Max Act: 0.0387. Min Act: -0.0002

Data Index: 737943 (C4 (Web Text))

Max Activating Token Index: 199

Text #6

Max Range: 0.0653. Min Range: -0.0653

Max Act: 0.0370. Min Act: -0.0002

Data Index: 1211447 (C4 (Web Text))

Max Activating Token Index: 255

Text #7

Max Range: 0.0653. Min Range: -0.0653

Max Act: 0.0349. Min Act: -0.0002

Data Index: 1148055 (C4 (Web Text))

Max Activating Token Index: 1017

Text #8

Max Range: 0.0653. Min Range: -0.0653

Max Act: 0.0327. Min Act: -0.0002

Data Index: 1018723 (C4 (Web Text))

Max Activating Token Index: 334

Text #9

Max Range: 0.0653. Min Range: -0.0653

Max Act: 0.0341. Min Act: -0.0002

Data Index: 115670 (C4 (Web Text))

Max Activating Token Index: 776

Text #10

Max Range: 0.0653. Min Range: -0.0653

Max Act: 0.0318. Min Act: -0.0002

Data Index: 769849 (C4 (Web Text))

Max Activating Token Index: 87

Text #11

Max Range: 0.0653. Min Range: -0.0653

Max Act: 0.0318. Min Act: -0.0002

Data Index: 1064813 (C4 (Web Text))

Max Activating Token Index: 140

Text #12

Max Range: 0.0653. Min Range: -0.0653

Max Act: 0.0347. Min Act: -0.0002

Data Index: 210386 (C4 (Web Text))

Max Activating Token Index: 473

Text #13

Max Range: 0.0653. Min Range: -0.0653

Max Act: 0.0325. Min Act: -0.0002

Data Index: 693977 (C4 (Web Text))

Max Activating Token Index: 939

Text #14

Max Range: 0.0653. Min Range: -0.0653

Max Act: 0.0317. Min Act: -0.0002

Data Index: 997074 (C4 (Web Text))

Max Activating Token Index: 334

Text #15

Max Range: 0.0653. Min Range: -0.0653

Max Act: 0.0313. Min Act: -0.0002

Data Index: 961029 (C4 (Web Text))

Max Activating Token Index: 10

Text #16

Max Range: 0.0653. Min Range: -0.0653

Max Act: 0.0303. Min Act: -0.0002

Data Index: 864583 (C4 (Web Text))

Max Activating Token Index: 771

Text #17

Max Range: 0.0653. Min Range: -0.0653

Max Act: 0.0289. Min Act: -0.0002

Data Index: 1073626 (C4 (Web Text))

Max Activating Token Index: 357

Text #18

Max Range: 0.0653. Min Range: -0.0653

Max Act: 0.0293. Min Act: -0.0002

Data Index: 716534 (C4 (Web Text))

Max Activating Token Index: 259

Text #19

Max Range: 0.0653. Min Range: -0.0653

Max Act: 0.0287. Min Act: -0.0002

Data Index: 257541 (C4 (Web Text))

Max Activating Token Index: 705