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

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

Neuron 226 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0289. Min Range: -2.0289

Max Act: 2.0289. Min Act: -0.0000

Data Index: 1033052 (C4 (Web Text))

Max Activating Token Index: 579

Text #1

Max Range: 2.0289. Min Range: -2.0289

Max Act: 1.6444. Min Act: -0.0000

Data Index: 966303 (C4 (Web Text))

Max Activating Token Index: 130

Text #2

Max Range: 2.0289. Min Range: -2.0289

Max Act: 1.4349. Min Act: -0.0000

Data Index: 135532 (C4 (Web Text))

Max Activating Token Index: 578

Text #3

Max Range: 2.0289. Min Range: -2.0289

Max Act: 1.6284. Min Act: -0.0000

Data Index: 331731 (C4 (Web Text))

Max Activating Token Index: 710

Text #4

Max Range: 2.0289. Min Range: -2.0289

Max Act: 1.6775. Min Act: -0.0000

Data Index: 361195 (C4 (Web Text))

Max Activating Token Index: 621

Text #5

Max Range: 2.0289. Min Range: -2.0289

Max Act: 1.5781. Min Act: -0.0000

Data Index: 213764 (C4 (Web Text))

Max Activating Token Index: 896

Text #6

Max Range: 2.0289. Min Range: -2.0289

Max Act: 1.4146. Min Act: -0.0000

Data Index: 609809 (C4 (Web Text))

Max Activating Token Index: 275

Text #7

Max Range: 2.0289. Min Range: -2.0289

Max Act: 1.4959. Min Act: -0.0000

Data Index: 1261871 (C4 (Web Text))

Max Activating Token Index: 890

Text #8

Max Range: 2.0289. Min Range: -2.0289

Max Act: 1.4068. Min Act: -0.0000

Data Index: 313809 (C4 (Web Text))

Max Activating Token Index: 770

Text #9

Max Range: 2.0289. Min Range: -2.0289

Max Act: 1.2904. Min Act: -0.0000

Data Index: 979654 (C4 (Web Text))

Max Activating Token Index: 937

Text #10

Max Range: 2.0289. Min Range: -2.0289

Max Act: 1.3204. Min Act: -0.0000

Data Index: 724331 (C4 (Web Text))

Max Activating Token Index: 703

Text #11

Max Range: 2.0289. Min Range: -2.0289

Max Act: 1.2280. Min Act: -0.0000

Data Index: 1321147 (C4 (Web Text))

Max Activating Token Index: 333

Text #12

Max Range: 2.0289. Min Range: -2.0289

Max Act: 1.2948. Min Act: -0.0000

Data Index: 863161 (C4 (Web Text))

Max Activating Token Index: 886

Text #13

Max Range: 2.0289. Min Range: -2.0289

Max Act: 1.2982. Min Act: -0.0000

Data Index: 79894 (C4 (Web Text))

Max Activating Token Index: 523

Text #14

Max Range: 2.0289. Min Range: -2.0289

Max Act: 1.2171. Min Act: -0.0000

Data Index: 1172533 (C4 (Web Text))

Max Activating Token Index: 99

Text #15

Max Range: 2.0289. Min Range: -2.0289

Max Act: 1.0971. Min Act: -0.0000

Data Index: 1444844 (Python Code)

Max Activating Token Index: 287

Text #16

Max Range: 2.0289. Min Range: -2.0289

Max Act: 1.3695. Min Act: -0.0000

Data Index: 842260 (C4 (Web Text))

Max Activating Token Index: 532

Text #17

Max Range: 2.0289. Min Range: -2.0289

Max Act: 1.2853. Min Act: -0.0000

Data Index: 1373438 (Python Code)

Max Activating Token Index: 451

Text #18

Max Range: 2.0289. Min Range: -2.0289

Max Act: 1.1608. Min Act: -0.0000

Data Index: 714532 (C4 (Web Text))

Max Activating Token Index: 27

Text #19

Max Range: 2.0289. Min Range: -2.0289

Max Act: 1.2188. Min Act: -0.0000

Data Index: 590501 (C4 (Web Text))

Max Activating Token Index: 838