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

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

Neuron 1029 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1002. Min Range: -1.1002

Max Act: 1.1002. Min Act: -0.0000

Data Index: 360345 (C4 (Web Text))

Max Activating Token Index: 148

Text #1

Max Range: 1.1002. Min Range: -1.1002

Max Act: 1.0440. Min Act: -0.0000

Data Index: 563661 (C4 (Web Text))

Max Activating Token Index: 967

Text #2

Max Range: 1.1002. Min Range: -1.1002

Max Act: 1.0365. Min Act: -0.0000

Data Index: 870049 (C4 (Web Text))

Max Activating Token Index: 1000

Text #3

Max Range: 1.1002. Min Range: -1.1002

Max Act: 0.8488. Min Act: 0.0001

Data Index: 213850 (C4 (Web Text))

Max Activating Token Index: 899

Text #4

Max Range: 1.1002. Min Range: -1.1002

Max Act: 0.8397. Min Act: -0.0000

Data Index: 1520276 (Python Code)

Max Activating Token Index: 252

Text #5

Max Range: 1.1002. Min Range: -1.1002

Max Act: 0.7371. Min Act: 0.0000

Data Index: 940977 (C4 (Web Text))

Max Activating Token Index: 200

Text #6

Max Range: 1.1002. Min Range: -1.1002

Max Act: 0.7557. Min Act: 0.0000

Data Index: 614567 (C4 (Web Text))

Max Activating Token Index: 412

Text #7

Max Range: 1.1002. Min Range: -1.1002

Max Act: 0.7366. Min Act: -0.0000

Data Index: 1317150 (C4 (Web Text))

Max Activating Token Index: 954

Text #8

Max Range: 1.1002. Min Range: -1.1002

Max Act: 0.6096. Min Act: -0.0000

Data Index: 546519 (C4 (Web Text))

Max Activating Token Index: 314

Text #9

Max Range: 1.1002. Min Range: -1.1002

Max Act: 0.6342. Min Act: -0.0000

Data Index: 89297 (C4 (Web Text))

Max Activating Token Index: 502

Text #10

Max Range: 1.1002. Min Range: -1.1002

Max Act: 0.6441. Min Act: 0.0001

Data Index: 1130580 (C4 (Web Text))

Max Activating Token Index: 984

Text #11

Max Range: 1.1002. Min Range: -1.1002

Max Act: 0.6254. Min Act: -0.0000

Data Index: 1030930 (C4 (Web Text))

Max Activating Token Index: 5

Text #12

Max Range: 1.1002. Min Range: -1.1002

Max Act: 0.6126. Min Act: -0.0000

Data Index: 1316633 (C4 (Web Text))

Max Activating Token Index: 510

Text #13

Max Range: 1.1002. Min Range: -1.1002

Max Act: 0.6495. Min Act: -0.0000

Data Index: 657476 (C4 (Web Text))

Max Activating Token Index: 185

Text #14

Max Range: 1.1002. Min Range: -1.1002

Max Act: 0.6228. Min Act: 0.0001

Data Index: 63182 (C4 (Web Text))

Max Activating Token Index: 343

Text #15

Max Range: 1.1002. Min Range: -1.1002

Max Act: 0.6255. Min Act: -0.0000

Data Index: 1414702 (Python Code)

Max Activating Token Index: 538

Text #16

Max Range: 1.1002. Min Range: -1.1002

Max Act: 0.6396. Min Act: -0.0000

Data Index: 1352177 (C4 (Web Text))

Max Activating Token Index: 618

Text #17

Max Range: 1.1002. Min Range: -1.1002

Max Act: 0.5813. Min Act: -0.0000

Data Index: 1168877 (C4 (Web Text))

Max Activating Token Index: 703

Text #18

Max Range: 1.1002. Min Range: -1.1002

Max Act: 0.5885. Min Act: -0.0000

Data Index: 1317467 (C4 (Web Text))

Max Activating Token Index: 692

Text #19

Max Range: 1.1002. Min Range: -1.1002

Max Act: 0.5989. Min Act: -0.0000

Data Index: 450005 (C4 (Web Text))

Max Activating Token Index: 709