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

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

Neuron 3574 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6210. Min Range: -0.6210

Max Act: 0.6210. Min Act: -0.0001

Data Index: 615453 (C4 (Web Text))

Max Activating Token Index: 344

Text #1

Max Range: 0.6210. Min Range: -0.6210

Max Act: 0.6078. Min Act: -0.0001

Data Index: 589567 (C4 (Web Text))

Max Activating Token Index: 334

Text #2

Max Range: 0.6210. Min Range: -0.6210

Max Act: 0.5826. Min Act: -0.0001

Data Index: 1253461 (C4 (Web Text))

Max Activating Token Index: 827

Text #3

Max Range: 0.6210. Min Range: -0.6210

Max Act: 0.5093. Min Act: -0.0001

Data Index: 70704 (C4 (Web Text))

Max Activating Token Index: 177

Text #4

Max Range: 0.6210. Min Range: -0.6210

Max Act: 0.5276. Min Act: -0.0001

Data Index: 1122964 (C4 (Web Text))

Max Activating Token Index: 180

Text #5

Max Range: 0.6210. Min Range: -0.6210

Max Act: 0.4975. Min Act: -0.0001

Data Index: 1290172 (C4 (Web Text))

Max Activating Token Index: 100

Text #6

Max Range: 0.6210. Min Range: -0.6210

Max Act: 0.4625. Min Act: -0.0001

Data Index: 215270 (C4 (Web Text))

Max Activating Token Index: 204

Text #7

Max Range: 0.6210. Min Range: -0.6210

Max Act: 0.4572. Min Act: -0.0000

Data Index: 1015777 (C4 (Web Text))

Max Activating Token Index: 983

Text #8

Max Range: 0.6210. Min Range: -0.6210

Max Act: 0.4901. Min Act: -0.0001

Data Index: 623045 (C4 (Web Text))

Max Activating Token Index: 952

Text #9

Max Range: 0.6210. Min Range: -0.6210

Max Act: 0.4561. Min Act: -0.0001

Data Index: 370705 (C4 (Web Text))

Max Activating Token Index: 584

Text #10

Max Range: 0.6210. Min Range: -0.6210

Max Act: 0.4683. Min Act: -0.0001

Data Index: 912528 (C4 (Web Text))

Max Activating Token Index: 306

Text #11

Max Range: 0.6210. Min Range: -0.6210

Max Act: 0.4486. Min Act: -0.0001

Data Index: 1233102 (C4 (Web Text))

Max Activating Token Index: 83

Text #12

Max Range: 0.6210. Min Range: -0.6210

Max Act: 0.4374. Min Act: -0.0001

Data Index: 396260 (C4 (Web Text))

Max Activating Token Index: 1002

Text #13

Max Range: 0.6210. Min Range: -0.6210

Max Act: 0.4163. Min Act: -0.0000

Data Index: 297600 (C4 (Web Text))

Max Activating Token Index: 450

Text #14

Max Range: 0.6210. Min Range: -0.6210

Max Act: 0.4267. Min Act: -0.0001

Data Index: 331847 (C4 (Web Text))

Max Activating Token Index: 88

Text #15

Max Range: 0.6210. Min Range: -0.6210

Max Act: 0.4029. Min Act: -0.0001

Data Index: 708370 (C4 (Web Text))

Max Activating Token Index: 916

Text #16

Max Range: 0.6210. Min Range: -0.6210

Max Act: 0.3934. Min Act: -0.0001

Data Index: 1029293 (C4 (Web Text))

Max Activating Token Index: 911

Text #17

Max Range: 0.6210. Min Range: -0.6210

Max Act: 0.4150. Min Act: -0.0001

Data Index: 378938 (C4 (Web Text))

Max Activating Token Index: 55

Text #18

Max Range: 0.6210. Min Range: -0.6210

Max Act: 0.4011. Min Act: -0.0001

Data Index: 122835 (C4 (Web Text))

Max Activating Token Index: 689

Text #19

Max Range: 0.6210. Min Range: -0.6210

Max Act: 0.4128. Min Act: -0.0000

Data Index: 821245 (C4 (Web Text))

Max Activating Token Index: 121