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

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

Neuron 4167 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7835. Min Range: -1.7835

Max Act: 1.7835. Min Act: -0.0001

Data Index: 1270235 (C4 (Web Text))

Max Activating Token Index: 425

Text #1

Max Range: 1.7835. Min Range: -1.7835

Max Act: 1.5468. Min Act: -0.0001

Data Index: 207685 (C4 (Web Text))

Max Activating Token Index: 305

Text #2

Max Range: 1.7835. Min Range: -1.7835

Max Act: 1.4138. Min Act: -0.0001

Data Index: 1179954 (C4 (Web Text))

Max Activating Token Index: 356

Text #3

Max Range: 1.7835. Min Range: -1.7835

Max Act: 1.4953. Min Act: -0.0001

Data Index: 385353 (C4 (Web Text))

Max Activating Token Index: 352

Text #4

Max Range: 1.7835. Min Range: -1.7835

Max Act: 1.3858. Min Act: -0.0001

Data Index: 992511 (C4 (Web Text))

Max Activating Token Index: 287

Text #5

Max Range: 1.7835. Min Range: -1.7835

Max Act: 1.3706. Min Act: -0.0001

Data Index: 1046318 (C4 (Web Text))

Max Activating Token Index: 812

Text #6

Max Range: 1.7835. Min Range: -1.7835

Max Act: 1.3632. Min Act: -0.0001

Data Index: 275492 (C4 (Web Text))

Max Activating Token Index: 53

Text #7

Max Range: 1.7835. Min Range: -1.7835

Max Act: 1.4034. Min Act: -0.0001

Data Index: 661353 (C4 (Web Text))

Max Activating Token Index: 730

Text #8

Max Range: 1.7835. Min Range: -1.7835

Max Act: 1.3629. Min Act: -0.0001

Data Index: 881779 (C4 (Web Text))

Max Activating Token Index: 1013

Text #9

Max Range: 1.7835. Min Range: -1.7835

Max Act: 1.2821. Min Act: -0.0001

Data Index: 957955 (C4 (Web Text))

Max Activating Token Index: 232

Text #10

Max Range: 1.7835. Min Range: -1.7835

Max Act: 1.3135. Min Act: -0.0001

Data Index: 888575 (C4 (Web Text))

Max Activating Token Index: 650

Text #11

Max Range: 1.7835. Min Range: -1.7835

Max Act: 1.4234. Min Act: -0.0001

Data Index: 502035 (C4 (Web Text))

Max Activating Token Index: 1008

Text #12

Max Range: 1.7835. Min Range: -1.7835

Max Act: 1.2950. Min Act: -0.0001

Data Index: 1183921 (C4 (Web Text))

Max Activating Token Index: 121

Text #13

Max Range: 1.7835. Min Range: -1.7835

Max Act: 1.3372. Min Act: -0.0001

Data Index: 31043 (C4 (Web Text))

Max Activating Token Index: 775

Text #14

Max Range: 1.7835. Min Range: -1.7835

Max Act: 1.2975. Min Act: -0.0001

Data Index: 482715 (C4 (Web Text))

Max Activating Token Index: 207

Text #15

Max Range: 1.7835. Min Range: -1.7835

Max Act: 1.3284. Min Act: -0.0001

Data Index: 315458 (C4 (Web Text))

Max Activating Token Index: 635

Text #16

Max Range: 1.7835. Min Range: -1.7835

Max Act: 1.3150. Min Act: -0.0001

Data Index: 663657 (C4 (Web Text))

Max Activating Token Index: 930

Text #17

Max Range: 1.7835. Min Range: -1.7835

Max Act: 1.2367. Min Act: -0.0001

Data Index: 933976 (C4 (Web Text))

Max Activating Token Index: 968

Text #18

Max Range: 1.7835. Min Range: -1.7835

Max Act: 1.2387. Min Act: -0.0001

Data Index: 1056917 (C4 (Web Text))

Max Activating Token Index: 137

Text #19

Max Range: 1.7835. Min Range: -1.7835

Max Act: 1.2466. Min Act: -0.0001

Data Index: 292411 (C4 (Web Text))

Max Activating Token Index: 121