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

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

Neuron 3824 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: 1.2045. Min Range: -1.2045

Max Act: 1.2045. Min Act: -0.0001

Data Index: 388274 (C4 (Web Text))

Max Activating Token Index: 882

Text #1

Max Range: 1.2045. Min Range: -1.2045

Max Act: 1.1163. Min Act: -0.0000

Data Index: 417628 (C4 (Web Text))

Max Activating Token Index: 115

Text #2

Max Range: 1.2045. Min Range: -1.2045

Max Act: 1.0781. Min Act: -0.0001

Data Index: 1252608 (C4 (Web Text))

Max Activating Token Index: 688

Text #3

Max Range: 1.2045. Min Range: -1.2045

Max Act: 1.1358. Min Act: -0.0000

Data Index: 983858 (C4 (Web Text))

Max Activating Token Index: 622

Text #4

Max Range: 1.2045. Min Range: -1.2045

Max Act: 1.0300. Min Act: -0.0000

Data Index: 347966 (C4 (Web Text))

Max Activating Token Index: 693

Text #5

Max Range: 1.2045. Min Range: -1.2045

Max Act: 0.9931. Min Act: -0.0000

Data Index: 896889 (C4 (Web Text))

Max Activating Token Index: 885

Text #6

Max Range: 1.2045. Min Range: -1.2045

Max Act: 0.9445. Min Act: -0.0001

Data Index: 760185 (C4 (Web Text))

Max Activating Token Index: 816

Text #7

Max Range: 1.2045. Min Range: -1.2045

Max Act: 0.8806. Min Act: -0.0000

Data Index: 1094445 (C4 (Web Text))

Max Activating Token Index: 350

Text #8

Max Range: 1.2045. Min Range: -1.2045

Max Act: 0.9005. Min Act: -0.0001

Data Index: 439921 (C4 (Web Text))

Max Activating Token Index: 45

Text #9

Max Range: 1.2045. Min Range: -1.2045

Max Act: 0.8986. Min Act: -0.0001

Data Index: 1363754 (Python Code)

Max Activating Token Index: 190

Text #10

Max Range: 1.2045. Min Range: -1.2045

Max Act: 0.9253. Min Act: -0.0001

Data Index: 852390 (C4 (Web Text))

Max Activating Token Index: 229

Text #11

Max Range: 1.2045. Min Range: -1.2045

Max Act: 0.8293. Min Act: -0.0000

Data Index: 573549 (C4 (Web Text))

Max Activating Token Index: 511

Text #12

Max Range: 1.2045. Min Range: -1.2045

Max Act: 0.8670. Min Act: -0.0000

Data Index: 807739 (C4 (Web Text))

Max Activating Token Index: 860

Text #13

Max Range: 1.2045. Min Range: -1.2045

Max Act: 0.8578. Min Act: -0.0001

Data Index: 580190 (C4 (Web Text))

Max Activating Token Index: 441

Text #14

Max Range: 1.2045. Min Range: -1.2045

Max Act: 0.8668. Min Act: -0.0000

Data Index: 163016 (C4 (Web Text))

Max Activating Token Index: 378

Text #15

Max Range: 1.2045. Min Range: -1.2045

Max Act: 0.8661. Min Act: -0.0000

Data Index: 257170 (C4 (Web Text))

Max Activating Token Index: 226

Text #16

Max Range: 1.2045. Min Range: -1.2045

Max Act: 0.7775. Min Act: -0.0001

Data Index: 1128214 (C4 (Web Text))

Max Activating Token Index: 557

Text #17

Max Range: 1.2045. Min Range: -1.2045

Max Act: 0.7774. Min Act: -0.0000

Data Index: 668687 (C4 (Web Text))

Max Activating Token Index: 311

Text #18

Max Range: 1.2045. Min Range: -1.2045

Max Act: 0.8019. Min Act: -0.0000

Data Index: 795365 (C4 (Web Text))

Max Activating Token Index: 546

Text #19

Max Range: 1.2045. Min Range: -1.2045

Max Act: 0.7974. Min Act: -0.0001

Data Index: 1399951 (Python Code)

Max Activating Token Index: 305