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

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

Neuron 2823 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: 0.6699. Min Range: -0.6699

Max Act: 0.6699. Min Act: -0.0001

Data Index: 25552 (C4 (Web Text))

Max Activating Token Index: 858

Text #1

Max Range: 0.6699. Min Range: -0.6699

Max Act: 0.4607. Min Act: -0.0001

Data Index: 1225268 (C4 (Web Text))

Max Activating Token Index: 697

Text #2

Max Range: 0.6699. Min Range: -0.6699

Max Act: 0.4450. Min Act: -0.0001

Data Index: 1531882 (Python Code)

Max Activating Token Index: 23

Text #3

Max Range: 0.6699. Min Range: -0.6699

Max Act: 0.4232. Min Act: -0.0001

Data Index: 291704 (C4 (Web Text))

Max Activating Token Index: 305

Text #4

Max Range: 0.6699. Min Range: -0.6699

Max Act: 0.4020. Min Act: -0.0001

Data Index: 1105734 (C4 (Web Text))

Max Activating Token Index: 191

Text #5

Max Range: 0.6699. Min Range: -0.6699

Max Act: 0.4114. Min Act: -0.0001

Data Index: 527717 (C4 (Web Text))

Max Activating Token Index: 858

Text #6

Max Range: 0.6699. Min Range: -0.6699

Max Act: 0.4054. Min Act: -0.0001

Data Index: 1596719 (Python Code)

Max Activating Token Index: 208

Text #7

Max Range: 0.6699. Min Range: -0.6699

Max Act: 0.4042. Min Act: -0.0001

Data Index: 1436359 (Python Code)

Max Activating Token Index: 190

Text #8

Max Range: 0.6699. Min Range: -0.6699

Max Act: 0.3561. Min Act: -0.0001

Data Index: 1022942 (C4 (Web Text))

Max Activating Token Index: 640

Text #9

Max Range: 0.6699. Min Range: -0.6699

Max Act: 0.4191. Min Act: -0.0001

Data Index: 1186713 (C4 (Web Text))

Max Activating Token Index: 697

Text #10

Max Range: 0.6699. Min Range: -0.6699

Max Act: 0.3609. Min Act: -0.0001

Data Index: 1369610 (Python Code)

Max Activating Token Index: 443

Text #11

Max Range: 0.6699. Min Range: -0.6699

Max Act: 0.3103. Min Act: -0.0001

Data Index: 336136 (C4 (Web Text))

Max Activating Token Index: 865

Text #12

Max Range: 0.6699. Min Range: -0.6699

Max Act: 0.3378. Min Act: -0.0001

Data Index: 968946 (C4 (Web Text))

Max Activating Token Index: 254

Text #13

Max Range: 0.6699. Min Range: -0.6699

Max Act: 0.3366. Min Act: -0.0001

Data Index: 1576776 (Python Code)

Max Activating Token Index: 499

Text #14

Max Range: 0.6699. Min Range: -0.6699

Max Act: 0.3094. Min Act: -0.0001

Data Index: 1597455 (Python Code)

Max Activating Token Index: 33

Text #15

Max Range: 0.6699. Min Range: -0.6699

Max Act: 0.2986. Min Act: -0.0001

Data Index: 1454425 (Python Code)

Max Activating Token Index: 602

Text #16

Max Range: 0.6699. Min Range: -0.6699

Max Act: 0.3178. Min Act: -0.0001

Data Index: 1647857 (Python Code)

Max Activating Token Index: 292

Text #17

Max Range: 0.6699. Min Range: -0.6699

Max Act: 0.3256. Min Act: -0.0001

Data Index: 1547031 (Python Code)

Max Activating Token Index: 22

Text #18

Max Range: 0.6699. Min Range: -0.6699

Max Act: 0.3273. Min Act: -0.0001

Data Index: 1133990 (C4 (Web Text))

Max Activating Token Index: 975

Text #19

Max Range: 0.6699. Min Range: -0.6699

Max Act: 0.3395. Min Act: -0.0001

Data Index: 1481927 (Python Code)

Max Activating Token Index: 377