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

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

Neuron 987 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: 1.9314. Min Range: -1.9314

Max Act: 1.9314. Min Act: -0.0000

Data Index: 676586 (C4 (Web Text))

Max Activating Token Index: 296

Text #1

Max Range: 1.9314. Min Range: -1.9314

Max Act: 1.4037. Min Act: -0.0000

Data Index: 394084 (C4 (Web Text))

Max Activating Token Index: 520

Text #2

Max Range: 1.9314. Min Range: -1.9314

Max Act: 1.2927. Min Act: -0.0000

Data Index: 1407001 (Python Code)

Max Activating Token Index: 916

Text #3

Max Range: 1.9314. Min Range: -1.9314

Max Act: 1.3531. Min Act: -0.0000

Data Index: 341625 (C4 (Web Text))

Max Activating Token Index: 464

Text #4

Max Range: 1.9314. Min Range: -1.9314

Max Act: 1.5167. Min Act: -0.0000

Data Index: 463523 (C4 (Web Text))

Max Activating Token Index: 1018

Text #5

Max Range: 1.9314. Min Range: -1.9314

Max Act: 1.3332. Min Act: -0.0000

Data Index: 1028131 (C4 (Web Text))

Max Activating Token Index: 36

Text #6

Max Range: 1.9314. Min Range: -1.9314

Max Act: 1.3170. Min Act: -0.0000

Data Index: 828329 (C4 (Web Text))

Max Activating Token Index: 359

Text #7

Max Range: 1.9314. Min Range: -1.9314

Max Act: 1.3235. Min Act: -0.0000

Data Index: 1537884 (Python Code)

Max Activating Token Index: 505

Text #8

Max Range: 1.9314. Min Range: -1.9314

Max Act: 1.3173. Min Act: -0.0000

Data Index: 1642201 (Python Code)

Max Activating Token Index: 726

Text #9

Max Range: 1.9314. Min Range: -1.9314

Max Act: 0.9862. Min Act: -0.0000

Data Index: 1276321 (C4 (Web Text))

Max Activating Token Index: 849

Text #10

Max Range: 1.9314. Min Range: -1.9314

Max Act: 1.1882. Min Act: -0.0000

Data Index: 1409293 (Python Code)

Max Activating Token Index: 526

Text #11

Max Range: 1.9314. Min Range: -1.9314

Max Act: 1.1484. Min Act: -0.0000

Data Index: 333854 (C4 (Web Text))

Max Activating Token Index: 255

Text #12

Max Range: 1.9314. Min Range: -1.9314

Max Act: 1.0979. Min Act: -0.0000

Data Index: 161770 (C4 (Web Text))

Max Activating Token Index: 79

Text #13

Max Range: 1.9314. Min Range: -1.9314

Max Act: 1.0717. Min Act: -0.0000

Data Index: 1059021 (C4 (Web Text))

Max Activating Token Index: 166

Text #14

Max Range: 1.9314. Min Range: -1.9314

Max Act: 1.1864. Min Act: -0.0000

Data Index: 591816 (C4 (Web Text))

Max Activating Token Index: 130

Text #15

Max Range: 1.9314. Min Range: -1.9314

Max Act: 1.1616. Min Act: -0.0000

Data Index: 1538430 (Python Code)

Max Activating Token Index: 922

Text #16

Max Range: 1.9314. Min Range: -1.9314

Max Act: 1.0545. Min Act: -0.0000

Data Index: 641275 (C4 (Web Text))

Max Activating Token Index: 388

Text #17

Max Range: 1.9314. Min Range: -1.9314

Max Act: 1.2049. Min Act: -0.0000

Data Index: 1605993 (Python Code)

Max Activating Token Index: 170

Text #18

Max Range: 1.9314. Min Range: -1.9314

Max Act: 1.1111. Min Act: -0.0000

Data Index: 734476 (C4 (Web Text))

Max Activating Token Index: 495

Text #19

Max Range: 1.9314. Min Range: -1.9314

Max Act: 1.0713. Min Act: -0.0000

Data Index: 139112 (C4 (Web Text))

Max Activating Token Index: 574