Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 681 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 1.5401. Min Range: -1.5401

Max Act: 1.5401. Min Act: -0.0001

Data Index: 1148375 (C4 (Web Text))

Max Activating Token Index: 893

Text #1

Max Range: 1.5401. Min Range: -1.5401

Max Act: 1.5392. Min Act: -0.0001

Data Index: 628184 (C4 (Web Text))

Max Activating Token Index: 284

Text #2

Max Range: 1.5401. Min Range: -1.5401

Max Act: 1.5279. Min Act: -0.0001

Data Index: 1329297 (C4 (Web Text))

Max Activating Token Index: 257

Text #3

Max Range: 1.5401. Min Range: -1.5401

Max Act: 1.2685. Min Act: -0.0001

Data Index: 924443 (C4 (Web Text))

Max Activating Token Index: 537

Text #4

Max Range: 1.5401. Min Range: -1.5401

Max Act: 1.3727. Min Act: -0.0001

Data Index: 856131 (C4 (Web Text))

Max Activating Token Index: 104

Text #5

Max Range: 1.5401. Min Range: -1.5401

Max Act: 1.2060. Min Act: -0.0001

Data Index: 655747 (C4 (Web Text))

Max Activating Token Index: 115

Text #6

Max Range: 1.5401. Min Range: -1.5401

Max Act: 1.3229. Min Act: -0.0001

Data Index: 446711 (C4 (Web Text))

Max Activating Token Index: 702

Text #7

Max Range: 1.5401. Min Range: -1.5401

Max Act: 1.3965. Min Act: -0.0001

Data Index: 989488 (C4 (Web Text))

Max Activating Token Index: 12

Text #8

Max Range: 1.5401. Min Range: -1.5401

Max Act: 1.4582. Min Act: -0.0001

Data Index: 1095652 (C4 (Web Text))

Max Activating Token Index: 910

Text #9

Max Range: 1.5401. Min Range: -1.5401

Max Act: 1.2759. Min Act: -0.0001

Data Index: 1213681 (C4 (Web Text))

Max Activating Token Index: 351

Text #10

Max Range: 1.5401. Min Range: -1.5401

Max Act: 1.3161. Min Act: -0.0001

Data Index: 1318385 (C4 (Web Text))

Max Activating Token Index: 120

Text #11

Max Range: 1.5401. Min Range: -1.5401

Max Act: 1.3837. Min Act: -0.0001

Data Index: 355345 (C4 (Web Text))

Max Activating Token Index: 980

Text #12

Max Range: 1.5401. Min Range: -1.5401

Max Act: 1.3391. Min Act: -0.0001

Data Index: 865360 (C4 (Web Text))

Max Activating Token Index: 38

Text #13

Max Range: 1.5401. Min Range: -1.5401

Max Act: 1.3775. Min Act: -0.0001

Data Index: 886192 (C4 (Web Text))

Max Activating Token Index: 953

Text #14

Max Range: 1.5401. Min Range: -1.5401

Max Act: 1.3429. Min Act: -0.0001

Data Index: 306975 (C4 (Web Text))

Max Activating Token Index: 893

Text #15

Max Range: 1.5401. Min Range: -1.5401

Max Act: 1.2274. Min Act: -0.0001

Data Index: 8565 (C4 (Web Text))

Max Activating Token Index: 578

Text #16

Max Range: 1.5401. Min Range: -1.5401

Max Act: 1.3007. Min Act: -0.0001

Data Index: 1210648 (C4 (Web Text))

Max Activating Token Index: 976

Text #17

Max Range: 1.5401. Min Range: -1.5401

Max Act: 1.1944. Min Act: -0.0001

Data Index: 239551 (C4 (Web Text))

Max Activating Token Index: 877

Text #18

Max Range: 1.5401. Min Range: -1.5401

Max Act: 1.1937. Min Act: -0.0001

Data Index: 256712 (C4 (Web Text))

Max Activating Token Index: 464

Text #19

Max Range: 1.5401. Min Range: -1.5401

Max Act: 1.1756. Min Act: -0.0001

Data Index: 848275 (C4 (Web Text))

Max Activating Token Index: 890