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

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

Neuron 948 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 4.1289. Min Range: -4.1289

Max Act: 4.1289. Min Act: -0.0000

Data Index: 29725 (C4 (Web Text))

Max Activating Token Index: 708

Text #1

Max Range: 4.1289. Min Range: -4.1289

Max Act: 3.7395. Min Act: -0.0000

Data Index: 503738 (C4 (Web Text))

Max Activating Token Index: 1020

Text #2

Max Range: 4.1289. Min Range: -4.1289

Max Act: 3.5641. Min Act: -0.0000

Data Index: 128934 (C4 (Web Text))

Max Activating Token Index: 828

Text #3

Max Range: 4.1289. Min Range: -4.1289

Max Act: 3.5176. Min Act: -0.0000

Data Index: 317294 (C4 (Web Text))

Max Activating Token Index: 866

Text #4

Max Range: 4.1289. Min Range: -4.1289

Max Act: 3.5660. Min Act: -0.0000

Data Index: 359795 (C4 (Web Text))

Max Activating Token Index: 650

Text #5

Max Range: 4.1289. Min Range: -4.1289

Max Act: 3.2683. Min Act: -0.0000

Data Index: 1321672 (C4 (Web Text))

Max Activating Token Index: 864

Text #6

Max Range: 4.1289. Min Range: -4.1289

Max Act: 3.0761. Min Act: -0.0000

Data Index: 283357 (C4 (Web Text))

Max Activating Token Index: 784

Text #7

Max Range: 4.1289. Min Range: -4.1289

Max Act: 3.5714. Min Act: -0.0000

Data Index: 1044921 (C4 (Web Text))

Max Activating Token Index: 142

Text #8

Max Range: 4.1289. Min Range: -4.1289

Max Act: 3.2236. Min Act: -0.0000

Data Index: 1266595 (C4 (Web Text))

Max Activating Token Index: 323

Text #9

Max Range: 4.1289. Min Range: -4.1289

Max Act: 3.1917. Min Act: -0.0000

Data Index: 1202594 (C4 (Web Text))

Max Activating Token Index: 336

Text #10

Max Range: 4.1289. Min Range: -4.1289

Max Act: 3.0520. Min Act: -0.0000

Data Index: 499226 (C4 (Web Text))

Max Activating Token Index: 913

Text #11

Max Range: 4.1289. Min Range: -4.1289

Max Act: 3.3129. Min Act: -0.0000

Data Index: 484288 (C4 (Web Text))

Max Activating Token Index: 619

Text #12

Max Range: 4.1289. Min Range: -4.1289

Max Act: 3.1269. Min Act: -0.0000

Data Index: 1289631 (C4 (Web Text))

Max Activating Token Index: 455

Text #13

Max Range: 4.1289. Min Range: -4.1289

Max Act: 3.2369. Min Act: -0.0000

Data Index: 901446 (C4 (Web Text))

Max Activating Token Index: 311

Text #14

Max Range: 4.1289. Min Range: -4.1289

Max Act: 3.0901. Min Act: -0.0000

Data Index: 21526 (C4 (Web Text))

Max Activating Token Index: 366

Text #15

Max Range: 4.1289. Min Range: -4.1289

Max Act: 3.0597. Min Act: -0.0000

Data Index: 1281076 (C4 (Web Text))

Max Activating Token Index: 940

Text #16

Max Range: 4.1289. Min Range: -4.1289

Max Act: 3.0551. Min Act: -0.0000

Data Index: 254727 (C4 (Web Text))

Max Activating Token Index: 395

Text #17

Max Range: 4.1289. Min Range: -4.1289

Max Act: 3.1889. Min Act: -0.0000

Data Index: 388831 (C4 (Web Text))

Max Activating Token Index: 962

Text #18

Max Range: 4.1289. Min Range: -4.1289

Max Act: 3.0346. Min Act: -0.0000

Data Index: 181591 (C4 (Web Text))

Max Activating Token Index: 75

Text #19

Max Range: 4.1289. Min Range: -4.1289

Max Act: 3.1475. Min Act: -0.0000

Data Index: 172444 (C4 (Web Text))

Max Activating Token Index: 615