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

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

Neuron 4751 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: 0.0583. Min Range: -0.0583

Max Act: 0.0583. Min Act: -0.0000

Data Index: 321202 (C4 (Web Text))

Max Activating Token Index: 211

Text #1

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0440. Min Act: -0.0000

Data Index: 1506576 (Python Code)

Max Activating Token Index: 815

Text #2

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0379. Min Act: -0.0000

Data Index: 1607456 (Python Code)

Max Activating Token Index: 985

Text #3

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0393. Min Act: -0.0000

Data Index: 741250 (C4 (Web Text))

Max Activating Token Index: 774

Text #4

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0393. Min Act: -0.0000

Data Index: 1078897 (C4 (Web Text))

Max Activating Token Index: 818

Text #5

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0398. Min Act: -0.0000

Data Index: 234226 (C4 (Web Text))

Max Activating Token Index: 339

Text #6

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0367. Min Act: -0.0000

Data Index: 1222001 (C4 (Web Text))

Max Activating Token Index: 662

Text #7

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0355. Min Act: -0.0000

Data Index: 1649321 (Python Code)

Max Activating Token Index: 636

Text #8

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0350. Min Act: -0.0000

Data Index: 1140434 (C4 (Web Text))

Max Activating Token Index: 437

Text #9

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0331. Min Act: -0.0000

Data Index: 1587892 (Python Code)

Max Activating Token Index: 563

Text #10

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0347. Min Act: -0.0000

Data Index: 1304039 (C4 (Web Text))

Max Activating Token Index: 369

Text #11

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0324. Min Act: -0.0000

Data Index: 1148954 (C4 (Web Text))

Max Activating Token Index: 842

Text #12

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0305. Min Act: -0.0000

Data Index: 1084833 (C4 (Web Text))

Max Activating Token Index: 784

Text #13

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0314. Min Act: -0.0000

Data Index: 1174224 (C4 (Web Text))

Max Activating Token Index: 901

Text #14

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0322. Min Act: -0.0000

Data Index: 1312878 (C4 (Web Text))

Max Activating Token Index: 861

Text #15

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0330. Min Act: -0.0000

Data Index: 776240 (C4 (Web Text))

Max Activating Token Index: 314

Text #16

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0343. Min Act: -0.0001

Data Index: 1572532 (Python Code)

Max Activating Token Index: 793

Text #17

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0326. Min Act: -0.0000

Data Index: 792377 (C4 (Web Text))

Max Activating Token Index: 677

Text #18

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0315. Min Act: -0.0001

Data Index: 872212 (C4 (Web Text))

Max Activating Token Index: 164

Text #19

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0311. Min Act: -0.0000

Data Index: 666146 (C4 (Web Text))

Max Activating Token Index: 569