Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3041 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.5382. Min Range: -0.5382

Max Act: 0.5131. Min Act: -0.0002

Data Index: 1030944 (C4 (Web Text))

Max Activating Token Index: 7

Text #1

Max Range: 0.5382. Min Range: -0.5382

Max Act: 0.5056. Min Act: -0.0002

Data Index: 1069550 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.5382. Min Range: -0.5382

Max Act: 0.4922. Min Act: -0.0002

Data Index: 474618 (C4 (Web Text))

Max Activating Token Index: 882

Text #3

Max Range: 0.5382. Min Range: -0.5382

Max Act: 0.5382. Min Act: -0.0001

Data Index: 1621879 (Python Code)

Max Activating Token Index: 244

Text #4

Max Range: 0.5382. Min Range: -0.5382

Max Act: 0.4861. Min Act: -0.0002

Data Index: 847710 (C4 (Web Text))

Max Activating Token Index: 68

Text #5

Max Range: 0.5382. Min Range: -0.5382

Max Act: 0.4915. Min Act: -0.0001

Data Index: 655651 (C4 (Web Text))

Max Activating Token Index: 853

Text #6

Max Range: 0.5382. Min Range: -0.5382

Max Act: 0.4268. Min Act: -0.0002

Data Index: 950035 (C4 (Web Text))

Max Activating Token Index: 159

Text #7

Max Range: 0.5382. Min Range: -0.5382

Max Act: 0.4397. Min Act: -0.0001

Data Index: 1617550 (Python Code)

Max Activating Token Index: 320

Text #8

Max Range: 0.5382. Min Range: -0.5382

Max Act: 0.4379. Min Act: -0.0001

Data Index: 1474660 (Python Code)

Max Activating Token Index: 514

Text #9

Max Range: 0.5382. Min Range: -0.5382

Max Act: 0.3995. Min Act: -0.0002

Data Index: 192348 (C4 (Web Text))

Max Activating Token Index: 757

Text #10

Max Range: 0.5382. Min Range: -0.5382

Max Act: 0.3811. Min Act: -0.0002

Data Index: 365965 (C4 (Web Text))

Max Activating Token Index: 809

Text #11

Max Range: 0.5382. Min Range: -0.5382

Max Act: 0.4117. Min Act: -0.0001

Data Index: 1039271 (C4 (Web Text))

Max Activating Token Index: 50

Text #12

Max Range: 0.5382. Min Range: -0.5382

Max Act: 0.4285. Min Act: -0.0002

Data Index: 1047746 (C4 (Web Text))

Max Activating Token Index: 716

Text #13

Max Range: 0.5382. Min Range: -0.5382

Max Act: 0.4234. Min Act: -0.0001

Data Index: 1066492 (C4 (Web Text))

Max Activating Token Index: 459

Text #14

Max Range: 0.5382. Min Range: -0.5382

Max Act: 0.4312. Min Act: -0.0002

Data Index: 886459 (C4 (Web Text))

Max Activating Token Index: 734

Text #15

Max Range: 0.5382. Min Range: -0.5382

Max Act: 0.4873. Min Act: -0.0002

Data Index: 462280 (C4 (Web Text))

Max Activating Token Index: 456

Text #16

Max Range: 0.5382. Min Range: -0.5382

Max Act: 0.4161. Min Act: -0.0001

Data Index: 641558 (C4 (Web Text))

Max Activating Token Index: 821

Text #17

Max Range: 0.5382. Min Range: -0.5382

Max Act: 0.3976. Min Act: -0.0002

Data Index: 752634 (C4 (Web Text))

Max Activating Token Index: 930

Text #18

Max Range: 0.5382. Min Range: -0.5382

Max Act: 0.4163. Min Act: -0.0002

Data Index: 1175800 (C4 (Web Text))

Max Activating Token Index: 857

Text #19

Max Range: 0.5382. Min Range: -0.5382

Max Act: 0.4544. Min Act: -0.0002

Data Index: 576877 (C4 (Web Text))

Max Activating Token Index: 829