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

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

Neuron 249 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: 0.4999. Min Range: -0.4999

Max Act: 0.4999. Min Act: -0.0001

Data Index: 886456 (C4 (Web Text))

Max Activating Token Index: 622

Text #1

Max Range: 0.4999. Min Range: -0.4999

Max Act: 0.4509. Min Act: -0.0001

Data Index: 416799 (C4 (Web Text))

Max Activating Token Index: 329

Text #2

Max Range: 0.4999. Min Range: -0.4999

Max Act: 0.4536. Min Act: -0.0001

Data Index: 1145528 (C4 (Web Text))

Max Activating Token Index: 720

Text #3

Max Range: 0.4999. Min Range: -0.4999

Max Act: 0.4050. Min Act: -0.0000

Data Index: 422825 (C4 (Web Text))

Max Activating Token Index: 111

Text #4

Max Range: 0.4999. Min Range: -0.4999

Max Act: 0.4172. Min Act: -0.0001

Data Index: 1265417 (C4 (Web Text))

Max Activating Token Index: 153

Text #5

Max Range: 0.4999. Min Range: -0.4999

Max Act: 0.4350. Min Act: -0.0001

Data Index: 161200 (C4 (Web Text))

Max Activating Token Index: 201

Text #6

Max Range: 0.4999. Min Range: -0.4999

Max Act: 0.4056. Min Act: -0.0001

Data Index: 1168248 (C4 (Web Text))

Max Activating Token Index: 448

Text #7

Max Range: 0.4999. Min Range: -0.4999

Max Act: 0.3954. Min Act: -0.0001

Data Index: 1256009 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 0.4999. Min Range: -0.4999

Max Act: 0.3820. Min Act: -0.0001

Data Index: 665499 (C4 (Web Text))

Max Activating Token Index: 294

Text #9

Max Range: 0.4999. Min Range: -0.4999

Max Act: 0.4187. Min Act: -0.0001

Data Index: 607520 (C4 (Web Text))

Max Activating Token Index: 547

Text #10

Max Range: 0.4999. Min Range: -0.4999

Max Act: 0.4028. Min Act: -0.0000

Data Index: 371 (C4 (Web Text))

Max Activating Token Index: 141

Text #11

Max Range: 0.4999. Min Range: -0.4999

Max Act: 0.4028. Min Act: -0.0000

Data Index: 455553 (C4 (Web Text))

Max Activating Token Index: 538

Text #12

Max Range: 0.4999. Min Range: -0.4999

Max Act: 0.3987. Min Act: -0.0001

Data Index: 277774 (C4 (Web Text))

Max Activating Token Index: 399

Text #13

Max Range: 0.4999. Min Range: -0.4999

Max Act: 0.4122. Min Act: -0.0001

Data Index: 1138045 (C4 (Web Text))

Max Activating Token Index: 525

Text #14

Max Range: 0.4999. Min Range: -0.4999

Max Act: 0.3952. Min Act: -0.0001

Data Index: 1086146 (C4 (Web Text))

Max Activating Token Index: 436

Text #15

Max Range: 0.4999. Min Range: -0.4999

Max Act: 0.3961. Min Act: -0.0001

Data Index: 1112102 (C4 (Web Text))

Max Activating Token Index: 282

Text #16

Max Range: 0.4999. Min Range: -0.4999

Max Act: 0.3788. Min Act: -0.0000

Data Index: 970776 (C4 (Web Text))

Max Activating Token Index: 56

Text #17

Max Range: 0.4999. Min Range: -0.4999

Max Act: 0.3896. Min Act: -0.0000

Data Index: 646829 (C4 (Web Text))

Max Activating Token Index: 612

Text #18

Max Range: 0.4999. Min Range: -0.4999

Max Act: 0.3727. Min Act: -0.0001

Data Index: 19822 (C4 (Web Text))

Max Activating Token Index: 592

Text #19

Max Range: 0.4999. Min Range: -0.4999

Max Act: 0.3978. Min Act: -0.0001

Data Index: 204484 (C4 (Web Text))

Max Activating Token Index: 691