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

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

Neuron 1068 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5661. Min Range: -0.5661

Max Act: 0.5661. Min Act: -0.0000

Data Index: 1278243 (C4 (Web Text))

Max Activating Token Index: 800

Text #1

Max Range: 0.5661. Min Range: -0.5661

Max Act: 0.4748. Min Act: -0.0000

Data Index: 589436 (C4 (Web Text))

Max Activating Token Index: 654

Text #2

Max Range: 0.5661. Min Range: -0.5661

Max Act: 0.4707. Min Act: -0.0001

Data Index: 1071619 (C4 (Web Text))

Max Activating Token Index: 216

Text #3

Max Range: 0.5661. Min Range: -0.5661

Max Act: 0.4732. Min Act: -0.0001

Data Index: 581741 (C4 (Web Text))

Max Activating Token Index: 487

Text #4

Max Range: 0.5661. Min Range: -0.5661

Max Act: 0.4439. Min Act: -0.0000

Data Index: 1086624 (C4 (Web Text))

Max Activating Token Index: 838

Text #5

Max Range: 0.5661. Min Range: -0.5661

Max Act: 0.4304. Min Act: -0.0000

Data Index: 65167 (C4 (Web Text))

Max Activating Token Index: 485

Text #6

Max Range: 0.5661. Min Range: -0.5661

Max Act: 0.4418. Min Act: -0.0000

Data Index: 1000815 (C4 (Web Text))

Max Activating Token Index: 183

Text #7

Max Range: 0.5661. Min Range: -0.5661

Max Act: 0.4528. Min Act: -0.0000

Data Index: 740270 (C4 (Web Text))

Max Activating Token Index: 199

Text #8

Max Range: 0.5661. Min Range: -0.5661

Max Act: 0.4000. Min Act: -0.0000

Data Index: 518891 (C4 (Web Text))

Max Activating Token Index: 876

Text #9

Max Range: 0.5661. Min Range: -0.5661

Max Act: 0.3955. Min Act: -0.0000

Data Index: 1020270 (C4 (Web Text))

Max Activating Token Index: 70

Text #10

Max Range: 0.5661. Min Range: -0.5661

Max Act: 0.3621. Min Act: -0.0000

Data Index: 1053275 (C4 (Web Text))

Max Activating Token Index: 267

Text #11

Max Range: 0.5661. Min Range: -0.5661

Max Act: 0.3627. Min Act: -0.0000

Data Index: 804687 (C4 (Web Text))

Max Activating Token Index: 861

Text #12

Max Range: 0.5661. Min Range: -0.5661

Max Act: 0.3691. Min Act: -0.0000

Data Index: 491638 (C4 (Web Text))

Max Activating Token Index: 1012

Text #13

Max Range: 0.5661. Min Range: -0.5661

Max Act: 0.3598. Min Act: -0.0001

Data Index: 320562 (C4 (Web Text))

Max Activating Token Index: 165

Text #14

Max Range: 0.5661. Min Range: -0.5661

Max Act: 0.3562. Min Act: -0.0000

Data Index: 903966 (C4 (Web Text))

Max Activating Token Index: 138

Text #15

Max Range: 0.5661. Min Range: -0.5661

Max Act: 0.3432. Min Act: -0.0001

Data Index: 741459 (C4 (Web Text))

Max Activating Token Index: 611

Text #16

Max Range: 0.5661. Min Range: -0.5661

Max Act: 0.3640. Min Act: -0.0000

Data Index: 1209880 (C4 (Web Text))

Max Activating Token Index: 891

Text #17

Max Range: 0.5661. Min Range: -0.5661

Max Act: 0.3576. Min Act: -0.0000

Data Index: 784451 (C4 (Web Text))

Max Activating Token Index: 835

Text #18

Max Range: 0.5661. Min Range: -0.5661

Max Act: 0.3402. Min Act: -0.0000

Data Index: 384150 (C4 (Web Text))

Max Activating Token Index: 410

Text #19

Max Range: 0.5661. Min Range: -0.5661

Max Act: 0.3372. Min Act: -0.0000

Data Index: 1104650 (C4 (Web Text))

Max Activating Token Index: 121