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

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

Neuron 4291 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5470. Min Range: -3.5470

Max Act: 3.5470. Min Act: -0.0000

Data Index: 260311 (C4 (Web Text))

Max Activating Token Index: 949

Text #1

Max Range: 3.5470. Min Range: -3.5470

Max Act: 3.2162. Min Act: -0.0000

Data Index: 1233860 (C4 (Web Text))

Max Activating Token Index: 379

Text #2

Max Range: 3.5470. Min Range: -3.5470

Max Act: 3.2926. Min Act: -0.0000

Data Index: 586993 (C4 (Web Text))

Max Activating Token Index: 569

Text #3

Max Range: 3.5470. Min Range: -3.5470

Max Act: 3.3729. Min Act: -0.0000

Data Index: 217177 (C4 (Web Text))

Max Activating Token Index: 109

Text #4

Max Range: 3.5470. Min Range: -3.5470

Max Act: 3.2135. Min Act: -0.0000

Data Index: 1372352 (Python Code)

Max Activating Token Index: 852

Text #5

Max Range: 3.5470. Min Range: -3.5470

Max Act: 3.1773. Min Act: -0.0000

Data Index: 140651 (C4 (Web Text))

Max Activating Token Index: 31

Text #6

Max Range: 3.5470. Min Range: -3.5470

Max Act: 3.1421. Min Act: -0.0000

Data Index: 309288 (C4 (Web Text))

Max Activating Token Index: 8

Text #7

Max Range: 3.5470. Min Range: -3.5470

Max Act: 3.0647. Min Act: -0.0000

Data Index: 493321 (C4 (Web Text))

Max Activating Token Index: 336

Text #8

Max Range: 3.5470. Min Range: -3.5470

Max Act: 3.2093. Min Act: -0.0000

Data Index: 1320629 (C4 (Web Text))

Max Activating Token Index: 34

Text #9

Max Range: 3.5470. Min Range: -3.5470

Max Act: 3.1338. Min Act: -0.0000

Data Index: 1651379 (Python Code)

Max Activating Token Index: 905

Text #10

Max Range: 3.5470. Min Range: -3.5470

Max Act: 2.8439. Min Act: -0.0000

Data Index: 310884 (C4 (Web Text))

Max Activating Token Index: 359

Text #11

Max Range: 3.5470. Min Range: -3.5470

Max Act: 3.0883. Min Act: -0.0000

Data Index: 1582361 (Python Code)

Max Activating Token Index: 966

Text #12

Max Range: 3.5470. Min Range: -3.5470

Max Act: 3.2187. Min Act: -0.0000

Data Index: 985667 (C4 (Web Text))

Max Activating Token Index: 522

Text #13

Max Range: 3.5470. Min Range: -3.5470

Max Act: 2.8977. Min Act: -0.0000

Data Index: 922451 (C4 (Web Text))

Max Activating Token Index: 909

Text #14

Max Range: 3.5470. Min Range: -3.5470

Max Act: 2.8236. Min Act: -0.0000

Data Index: 968968 (C4 (Web Text))

Max Activating Token Index: 122

Text #15

Max Range: 3.5470. Min Range: -3.5470

Max Act: 3.1639. Min Act: -0.0000

Data Index: 688721 (C4 (Web Text))

Max Activating Token Index: 557

Text #16

Max Range: 3.5470. Min Range: -3.5470

Max Act: 3.1057. Min Act: -0.0000

Data Index: 1314242 (C4 (Web Text))

Max Activating Token Index: 307

Text #17

Max Range: 3.5470. Min Range: -3.5470

Max Act: 3.1026. Min Act: -0.0000

Data Index: 67128 (C4 (Web Text))

Max Activating Token Index: 573

Text #18

Max Range: 3.5470. Min Range: -3.5470

Max Act: 2.7234. Min Act: -0.0000

Data Index: 1516284 (Python Code)

Max Activating Token Index: 805

Text #19

Max Range: 3.5470. Min Range: -3.5470

Max Act: 2.7394. Min Act: -0.0000

Data Index: 803343 (C4 (Web Text))

Max Activating Token Index: 563