Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3854 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.4926. Min Range: -0.4926

Max Act: 0.4926. Min Act: -0.0000

Data Index: 1357250 (C4 (Web Text))

Max Activating Token Index: 418

Text #1

Max Range: 0.4926. Min Range: -0.4926

Max Act: 0.3942. Min Act: -0.0000

Data Index: 457017 (C4 (Web Text))

Max Activating Token Index: 95

Text #2

Max Range: 0.4926. Min Range: -0.4926

Max Act: 0.3823. Min Act: -0.0000

Data Index: 355104 (C4 (Web Text))

Max Activating Token Index: 389

Text #3

Max Range: 0.4926. Min Range: -0.4926

Max Act: 0.3518. Min Act: -0.0000

Data Index: 1325330 (C4 (Web Text))

Max Activating Token Index: 179

Text #4

Max Range: 0.4926. Min Range: -0.4926

Max Act: 0.3599. Min Act: -0.0000

Data Index: 90397 (C4 (Web Text))

Max Activating Token Index: 387

Text #5

Max Range: 0.4926. Min Range: -0.4926

Max Act: 0.3667. Min Act: -0.0000

Data Index: 1201094 (C4 (Web Text))

Max Activating Token Index: 503

Text #6

Max Range: 0.4926. Min Range: -0.4926

Max Act: 0.3482. Min Act: -0.0000

Data Index: 761701 (C4 (Web Text))

Max Activating Token Index: 755

Text #7

Max Range: 0.4926. Min Range: -0.4926

Max Act: 0.3322. Min Act: -0.0000

Data Index: 1268172 (C4 (Web Text))

Max Activating Token Index: 893

Text #8

Max Range: 0.4926. Min Range: -0.4926

Max Act: 0.3334. Min Act: -0.0000

Data Index: 859452 (C4 (Web Text))

Max Activating Token Index: 697

Text #9

Max Range: 0.4926. Min Range: -0.4926

Max Act: 0.3442. Min Act: -0.0000

Data Index: 1039131 (C4 (Web Text))

Max Activating Token Index: 965

Text #10

Max Range: 0.4926. Min Range: -0.4926

Max Act: 0.3206. Min Act: -0.0000

Data Index: 158563 (C4 (Web Text))

Max Activating Token Index: 667

Text #11

Max Range: 0.4926. Min Range: -0.4926

Max Act: 0.3544. Min Act: -0.0000

Data Index: 1102899 (C4 (Web Text))

Max Activating Token Index: 459

Text #12

Max Range: 0.4926. Min Range: -0.4926

Max Act: 0.3395. Min Act: -0.0000

Data Index: 1005808 (C4 (Web Text))

Max Activating Token Index: 688

Text #13

Max Range: 0.4926. Min Range: -0.4926

Max Act: 0.3397. Min Act: -0.0000

Data Index: 870249 (C4 (Web Text))

Max Activating Token Index: 430

Text #14

Max Range: 0.4926. Min Range: -0.4926

Max Act: 0.3256. Min Act: -0.0000

Data Index: 58124 (C4 (Web Text))

Max Activating Token Index: 333

Text #15

Max Range: 0.4926. Min Range: -0.4926

Max Act: 0.3217. Min Act: -0.0000

Data Index: 864491 (C4 (Web Text))

Max Activating Token Index: 994

Text #16

Max Range: 0.4926. Min Range: -0.4926

Max Act: 0.3216. Min Act: -0.0000

Data Index: 219641 (C4 (Web Text))

Max Activating Token Index: 375

Text #17

Max Range: 0.4926. Min Range: -0.4926

Max Act: 0.3255. Min Act: -0.0000

Data Index: 2649 (C4 (Web Text))

Max Activating Token Index: 632

Text #18

Max Range: 0.4926. Min Range: -0.4926

Max Act: 0.3269. Min Act: -0.0000

Data Index: 119700 (C4 (Web Text))

Max Activating Token Index: 294

Text #19

Max Range: 0.4926. Min Range: -0.4926

Max Act: 0.3253. Min Act: -0.0000

Data Index: 205215 (C4 (Web Text))

Max Activating Token Index: 329