Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2771 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.6490. Min Range: -0.6490

Max Act: 0.6135. Min Act: -0.0000

Data Index: 1280342 (C4 (Web Text))

Max Activating Token Index: 877

Text #1

Max Range: 0.6490. Min Range: -0.6490

Max Act: 0.5931. Min Act: -0.0000

Data Index: 880221 (C4 (Web Text))

Max Activating Token Index: 997

Text #2

Max Range: 0.6490. Min Range: -0.6490

Max Act: 0.6490. Min Act: -0.0000

Data Index: 50758 (C4 (Web Text))

Max Activating Token Index: 809

Text #3

Max Range: 0.6490. Min Range: -0.6490

Max Act: 0.5621. Min Act: -0.0000

Data Index: 550341 (C4 (Web Text))

Max Activating Token Index: 92

Text #4

Max Range: 0.6490. Min Range: -0.6490

Max Act: 0.5356. Min Act: -0.0000

Data Index: 1310119 (C4 (Web Text))

Max Activating Token Index: 465

Text #5

Max Range: 0.6490. Min Range: -0.6490

Max Act: 0.5834. Min Act: -0.0000

Data Index: 1132376 (C4 (Web Text))

Max Activating Token Index: 218

Text #6

Max Range: 0.6490. Min Range: -0.6490

Max Act: 0.4944. Min Act: -0.0000

Data Index: 1138220 (C4 (Web Text))

Max Activating Token Index: 867

Text #7

Max Range: 0.6490. Min Range: -0.6490

Max Act: 0.5452. Min Act: -0.0000

Data Index: 9443 (C4 (Web Text))

Max Activating Token Index: 875

Text #8

Max Range: 0.6490. Min Range: -0.6490

Max Act: 0.5078. Min Act: -0.0000

Data Index: 411037 (C4 (Web Text))

Max Activating Token Index: 703

Text #9

Max Range: 0.6490. Min Range: -0.6490

Max Act: 0.5158. Min Act: -0.0000

Data Index: 643344 (C4 (Web Text))

Max Activating Token Index: 980

Text #10

Max Range: 0.6490. Min Range: -0.6490

Max Act: 0.4970. Min Act: -0.0000

Data Index: 320994 (C4 (Web Text))

Max Activating Token Index: 748

Text #11

Max Range: 0.6490. Min Range: -0.6490

Max Act: 0.5233. Min Act: -0.0000

Data Index: 955575 (C4 (Web Text))

Max Activating Token Index: 219

Text #12

Max Range: 0.6490. Min Range: -0.6490

Max Act: 0.5059. Min Act: -0.0000

Data Index: 312476 (C4 (Web Text))

Max Activating Token Index: 60

Text #13

Max Range: 0.6490. Min Range: -0.6490

Max Act: 0.5045. Min Act: -0.0000

Data Index: 289149 (C4 (Web Text))

Max Activating Token Index: 623

Text #14

Max Range: 0.6490. Min Range: -0.6490

Max Act: 0.4822. Min Act: -0.0000

Data Index: 1167417 (C4 (Web Text))

Max Activating Token Index: 412

Text #15

Max Range: 0.6490. Min Range: -0.6490

Max Act: 0.4678. Min Act: -0.0000

Data Index: 1231832 (C4 (Web Text))

Max Activating Token Index: 277

Text #16

Max Range: 0.6490. Min Range: -0.6490

Max Act: 0.4940. Min Act: -0.0000

Data Index: 635066 (C4 (Web Text))

Max Activating Token Index: 604

Text #17

Max Range: 0.6490. Min Range: -0.6490

Max Act: 0.4904. Min Act: -0.0000

Data Index: 465401 (C4 (Web Text))

Max Activating Token Index: 203

Text #18

Max Range: 0.6490. Min Range: -0.6490

Max Act: 0.5037. Min Act: -0.0000

Data Index: 746070 (C4 (Web Text))

Max Activating Token Index: 30

Text #19

Max Range: 0.6490. Min Range: -0.6490

Max Act: 0.4716. Min Act: -0.0000

Data Index: 256944 (C4 (Web Text))

Max Activating Token Index: 256