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

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

Neuron 706 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0328. Min Range: -1.0328

Max Act: 1.0328. Min Act: -0.0000

Data Index: 842001 (C4 (Web Text))

Max Activating Token Index: 535

Text #1

Max Range: 1.0328. Min Range: -1.0328

Max Act: 0.9570. Min Act: -0.0000

Data Index: 414518 (C4 (Web Text))

Max Activating Token Index: 709

Text #2

Max Range: 1.0328. Min Range: -1.0328

Max Act: 0.9146. Min Act: -0.0000

Data Index: 423838 (C4 (Web Text))

Max Activating Token Index: 961

Text #3

Max Range: 1.0328. Min Range: -1.0328

Max Act: 0.8720. Min Act: -0.0000

Data Index: 1297771 (C4 (Web Text))

Max Activating Token Index: 402

Text #4

Max Range: 1.0328. Min Range: -1.0328

Max Act: 0.8070. Min Act: 0.0000

Data Index: 1268985 (C4 (Web Text))

Max Activating Token Index: 272

Text #5

Max Range: 1.0328. Min Range: -1.0328

Max Act: 0.8510. Min Act: -0.0000

Data Index: 1249787 (C4 (Web Text))

Max Activating Token Index: 92

Text #6

Max Range: 1.0328. Min Range: -1.0328

Max Act: 0.8409. Min Act: -0.0000

Data Index: 1329080 (C4 (Web Text))

Max Activating Token Index: 633

Text #7

Max Range: 1.0328. Min Range: -1.0328

Max Act: 0.8424. Min Act: -0.0000

Data Index: 959211 (C4 (Web Text))

Max Activating Token Index: 298

Text #8

Max Range: 1.0328. Min Range: -1.0328

Max Act: 0.8273. Min Act: -0.0000

Data Index: 224573 (C4 (Web Text))

Max Activating Token Index: 697

Text #9

Max Range: 1.0328. Min Range: -1.0328

Max Act: 0.8127. Min Act: -0.0000

Data Index: 248895 (C4 (Web Text))

Max Activating Token Index: 344

Text #10

Max Range: 1.0328. Min Range: -1.0328

Max Act: 0.8414. Min Act: -0.0000

Data Index: 179677 (C4 (Web Text))

Max Activating Token Index: 90

Text #11

Max Range: 1.0328. Min Range: -1.0328

Max Act: 0.7898. Min Act: -0.0000

Data Index: 353150 (C4 (Web Text))

Max Activating Token Index: 180

Text #12

Max Range: 1.0328. Min Range: -1.0328

Max Act: 0.7307. Min Act: -0.0000

Data Index: 1638945 (Python Code)

Max Activating Token Index: 859

Text #13

Max Range: 1.0328. Min Range: -1.0328

Max Act: 0.7518. Min Act: -0.0000

Data Index: 501219 (C4 (Web Text))

Max Activating Token Index: 355

Text #14

Max Range: 1.0328. Min Range: -1.0328

Max Act: 0.8374. Min Act: -0.0000

Data Index: 743836 (C4 (Web Text))

Max Activating Token Index: 97

Text #15

Max Range: 1.0328. Min Range: -1.0328

Max Act: 0.6578. Min Act: -0.0000

Data Index: 850229 (C4 (Web Text))

Max Activating Token Index: 226

Text #16

Max Range: 1.0328. Min Range: -1.0328

Max Act: 0.7661. Min Act: -0.0000

Data Index: 579596 (C4 (Web Text))

Max Activating Token Index: 161

Text #17

Max Range: 1.0328. Min Range: -1.0328

Max Act: 0.7278. Min Act: -0.0000

Data Index: 525521 (C4 (Web Text))

Max Activating Token Index: 820

Text #18

Max Range: 1.0328. Min Range: -1.0328

Max Act: 0.7715. Min Act: -0.0000

Data Index: 963989 (C4 (Web Text))

Max Activating Token Index: 366

Text #19

Max Range: 1.0328. Min Range: -1.0328

Max Act: 0.7194. Min Act: -0.0000

Data Index: 962650 (C4 (Web Text))

Max Activating Token Index: 191