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

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

Neuron 2120 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2309. Min Range: -1.2309

Max Act: 0.8972. Min Act: -0.0000

Data Index: 134776 (C4 (Web Text))

Max Activating Token Index: 325

Text #1

Max Range: 1.2309. Min Range: -1.2309

Max Act: 1.2309. Min Act: -0.0000

Data Index: 969269 (C4 (Web Text))

Max Activating Token Index: 376

Text #2

Max Range: 1.2309. Min Range: -1.2309

Max Act: 1.1230. Min Act: -0.0000

Data Index: 851957 (C4 (Web Text))

Max Activating Token Index: 282

Text #3

Max Range: 1.2309. Min Range: -1.2309

Max Act: 1.0209. Min Act: -0.0001

Data Index: 380458 (C4 (Web Text))

Max Activating Token Index: 415

Text #4

Max Range: 1.2309. Min Range: -1.2309

Max Act: 0.9445. Min Act: -0.0000

Data Index: 944395 (C4 (Web Text))

Max Activating Token Index: 196

Text #5

Max Range: 1.2309. Min Range: -1.2309

Max Act: 1.0495. Min Act: -0.0001

Data Index: 600979 (C4 (Web Text))

Max Activating Token Index: 267

Text #6

Max Range: 1.2309. Min Range: -1.2309

Max Act: 0.9426. Min Act: -0.0000

Data Index: 1096311 (C4 (Web Text))

Max Activating Token Index: 936

Text #7

Max Range: 1.2309. Min Range: -1.2309

Max Act: 0.9230. Min Act: -0.0000

Data Index: 834931 (C4 (Web Text))

Max Activating Token Index: 382

Text #8

Max Range: 1.2309. Min Range: -1.2309

Max Act: 0.9880. Min Act: -0.0000

Data Index: 327685 (C4 (Web Text))

Max Activating Token Index: 743

Text #9

Max Range: 1.2309. Min Range: -1.2309

Max Act: 1.0218. Min Act: -0.0000

Data Index: 536948 (C4 (Web Text))

Max Activating Token Index: 159

Text #10

Max Range: 1.2309. Min Range: -1.2309

Max Act: 0.8707. Min Act: -0.0000

Data Index: 425908 (C4 (Web Text))

Max Activating Token Index: 207

Text #11

Max Range: 1.2309. Min Range: -1.2309

Max Act: 0.9039. Min Act: -0.0000

Data Index: 336414 (C4 (Web Text))

Max Activating Token Index: 914

Text #12

Max Range: 1.2309. Min Range: -1.2309

Max Act: 0.8787. Min Act: -0.0000

Data Index: 781887 (C4 (Web Text))

Max Activating Token Index: 393

Text #13

Max Range: 1.2309. Min Range: -1.2309

Max Act: 0.8589. Min Act: -0.0000

Data Index: 96883 (C4 (Web Text))

Max Activating Token Index: 557

Text #14

Max Range: 1.2309. Min Range: -1.2309

Max Act: 0.8063. Min Act: -0.0000

Data Index: 253540 (C4 (Web Text))

Max Activating Token Index: 750

Text #15

Max Range: 1.2309. Min Range: -1.2309

Max Act: 0.8174. Min Act: -0.0000

Data Index: 839855 (C4 (Web Text))

Max Activating Token Index: 341

Text #16

Max Range: 1.2309. Min Range: -1.2309

Max Act: 0.9249. Min Act: -0.0001

Data Index: 73194 (C4 (Web Text))

Max Activating Token Index: 467

Text #17

Max Range: 1.2309. Min Range: -1.2309

Max Act: 0.9709. Min Act: -0.0000

Data Index: 1307445 (C4 (Web Text))

Max Activating Token Index: 743

Text #18

Max Range: 1.2309. Min Range: -1.2309

Max Act: 0.8834. Min Act: -0.0000

Data Index: 421272 (C4 (Web Text))

Max Activating Token Index: 557

Text #19

Max Range: 1.2309. Min Range: -1.2309

Max Act: 0.8967. Min Act: -0.0000

Data Index: 1013396 (C4 (Web Text))

Max Activating Token Index: 118