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

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

Neuron 3318 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4312. Min Range: -3.4312

Max Act: 3.3382. Min Act: -0.0000

Data Index: 793627 (C4 (Web Text))

Max Activating Token Index: 352

Text #1

Max Range: 3.4312. Min Range: -3.4312

Max Act: 3.4312. Min Act: -0.0000

Data Index: 782162 (C4 (Web Text))

Max Activating Token Index: 245

Text #2

Max Range: 3.4312. Min Range: -3.4312

Max Act: 3.2430. Min Act: -0.0000

Data Index: 48990 (C4 (Web Text))

Max Activating Token Index: 377

Text #3

Max Range: 3.4312. Min Range: -3.4312

Max Act: 2.6930. Min Act: -0.0000

Data Index: 366599 (C4 (Web Text))

Max Activating Token Index: 880

Text #4

Max Range: 3.4312. Min Range: -3.4312

Max Act: 3.1524. Min Act: -0.0000

Data Index: 551409 (C4 (Web Text))

Max Activating Token Index: 900

Text #5

Max Range: 3.4312. Min Range: -3.4312

Max Act: 2.8635. Min Act: -0.0000

Data Index: 889496 (C4 (Web Text))

Max Activating Token Index: 339

Text #6

Max Range: 3.4312. Min Range: -3.4312

Max Act: 2.7201. Min Act: -0.0001

Data Index: 1262960 (C4 (Web Text))

Max Activating Token Index: 892

Text #7

Max Range: 3.4312. Min Range: -3.4312

Max Act: 2.6468. Min Act: -0.0000

Data Index: 886511 (C4 (Web Text))

Max Activating Token Index: 576

Text #8

Max Range: 3.4312. Min Range: -3.4312

Max Act: 2.8626. Min Act: -0.0000

Data Index: 1300618 (C4 (Web Text))

Max Activating Token Index: 415

Text #9

Max Range: 3.4312. Min Range: -3.4312

Max Act: 2.7882. Min Act: -0.0000

Data Index: 477170 (C4 (Web Text))

Max Activating Token Index: 131

Text #10

Max Range: 3.4312. Min Range: -3.4312

Max Act: 2.7430. Min Act: -0.0001

Data Index: 1244301 (C4 (Web Text))

Max Activating Token Index: 855

Text #11

Max Range: 3.4312. Min Range: -3.4312

Max Act: 2.5158. Min Act: -0.0000

Data Index: 651634 (C4 (Web Text))

Max Activating Token Index: 752

Text #12

Max Range: 3.4312. Min Range: -3.4312

Max Act: 2.4919. Min Act: -0.0000

Data Index: 505869 (C4 (Web Text))

Max Activating Token Index: 489

Text #13

Max Range: 3.4312. Min Range: -3.4312

Max Act: 2.4583. Min Act: -0.0000

Data Index: 36683 (C4 (Web Text))

Max Activating Token Index: 353

Text #14

Max Range: 3.4312. Min Range: -3.4312

Max Act: 2.1895. Min Act: -0.0000

Data Index: 1039288 (C4 (Web Text))

Max Activating Token Index: 309

Text #15

Max Range: 3.4312. Min Range: -3.4312

Max Act: 2.3301. Min Act: -0.0000

Data Index: 522463 (C4 (Web Text))

Max Activating Token Index: 440

Text #16

Max Range: 3.4312. Min Range: -3.4312

Max Act: 2.3221. Min Act: -0.0000

Data Index: 1616004 (Python Code)

Max Activating Token Index: 219

Text #17

Max Range: 3.4312. Min Range: -3.4312

Max Act: 2.2981. Min Act: -0.0000

Data Index: 607414 (C4 (Web Text))

Max Activating Token Index: 185

Text #18

Max Range: 3.4312. Min Range: -3.4312

Max Act: 2.5634. Min Act: -0.0000

Data Index: 764905 (C4 (Web Text))

Max Activating Token Index: 809

Text #19

Max Range: 3.4312. Min Range: -3.4312

Max Act: 2.3983. Min Act: -0.0000

Data Index: 585963 (C4 (Web Text))

Max Activating Token Index: 472