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

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

Neuron 3326 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3862. Min Range: -1.3862

Max Act: 1.3862. Min Act: -0.0000

Data Index: 359356 (C4 (Web Text))

Max Activating Token Index: 827

Text #1

Max Range: 1.3862. Min Range: -1.3862

Max Act: 1.3331. Min Act: -0.0000

Data Index: 339698 (C4 (Web Text))

Max Activating Token Index: 301

Text #2

Max Range: 1.3862. Min Range: -1.3862

Max Act: 1.2749. Min Act: -0.0000

Data Index: 841219 (C4 (Web Text))

Max Activating Token Index: 73

Text #3

Max Range: 1.3862. Min Range: -1.3862

Max Act: 1.3479. Min Act: -0.0000

Data Index: 812211 (C4 (Web Text))

Max Activating Token Index: 407

Text #4

Max Range: 1.3862. Min Range: -1.3862

Max Act: 1.3475. Min Act: -0.0000

Data Index: 964397 (C4 (Web Text))

Max Activating Token Index: 488

Text #5

Max Range: 1.3862. Min Range: -1.3862

Max Act: 1.3192. Min Act: -0.0000

Data Index: 1115467 (C4 (Web Text))

Max Activating Token Index: 227

Text #6

Max Range: 1.3862. Min Range: -1.3862

Max Act: 1.2048. Min Act: -0.0000

Data Index: 261887 (C4 (Web Text))

Max Activating Token Index: 63

Text #7

Max Range: 1.3862. Min Range: -1.3862

Max Act: 1.1695. Min Act: -0.0000

Data Index: 1293422 (C4 (Web Text))

Max Activating Token Index: 968

Text #8

Max Range: 1.3862. Min Range: -1.3862

Max Act: 1.1265. Min Act: -0.0000

Data Index: 1318000 (C4 (Web Text))

Max Activating Token Index: 119

Text #9

Max Range: 1.3862. Min Range: -1.3862

Max Act: 1.0969. Min Act: -0.0000

Data Index: 424507 (C4 (Web Text))

Max Activating Token Index: 663

Text #10

Max Range: 1.3862. Min Range: -1.3862

Max Act: 1.1010. Min Act: -0.0000

Data Index: 916611 (C4 (Web Text))

Max Activating Token Index: 788

Text #11

Max Range: 1.3862. Min Range: -1.3862

Max Act: 1.0996. Min Act: -0.0000

Data Index: 838639 (C4 (Web Text))

Max Activating Token Index: 710

Text #12

Max Range: 1.3862. Min Range: -1.3862

Max Act: 1.1778. Min Act: -0.0000

Data Index: 1074308 (C4 (Web Text))

Max Activating Token Index: 774

Text #13

Max Range: 1.3862. Min Range: -1.3862

Max Act: 1.0861. Min Act: -0.0000

Data Index: 185169 (C4 (Web Text))

Max Activating Token Index: 408

Text #14

Max Range: 1.3862. Min Range: -1.3862

Max Act: 1.1373. Min Act: -0.0000

Data Index: 1064947 (C4 (Web Text))

Max Activating Token Index: 975

Text #15

Max Range: 1.3862. Min Range: -1.3862

Max Act: 1.0573. Min Act: -0.0000

Data Index: 827425 (C4 (Web Text))

Max Activating Token Index: 377

Text #16

Max Range: 1.3862. Min Range: -1.3862

Max Act: 1.0088. Min Act: -0.0000

Data Index: 46323 (C4 (Web Text))

Max Activating Token Index: 107

Text #17

Max Range: 1.3862. Min Range: -1.3862

Max Act: 0.9873. Min Act: -0.0000

Data Index: 787358 (C4 (Web Text))

Max Activating Token Index: 819

Text #18

Max Range: 1.3862. Min Range: -1.3862

Max Act: 1.0747. Min Act: -0.0000

Data Index: 205062 (C4 (Web Text))

Max Activating Token Index: 267

Text #19

Max Range: 1.3862. Min Range: -1.3862

Max Act: 0.9647. Min Act: -0.0000

Data Index: 477303 (C4 (Web Text))

Max Activating Token Index: 689