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

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

Neuron 1318 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.9147. Min Range: -0.9147

Max Act: 0.9025. Min Act: -0.0001

Data Index: 1384891 (Python Code)

Max Activating Token Index: 684

Text #1

Max Range: 0.9147. Min Range: -0.9147

Max Act: 0.8366. Min Act: -0.0001

Data Index: 622193 (C4 (Web Text))

Max Activating Token Index: 112

Text #2

Max Range: 0.9147. Min Range: -0.9147

Max Act: 0.8586. Min Act: -0.0001

Data Index: 140892 (C4 (Web Text))

Max Activating Token Index: 13

Text #3

Max Range: 0.9147. Min Range: -0.9147

Max Act: 0.9147. Min Act: -0.0001

Data Index: 1398733 (Python Code)

Max Activating Token Index: 772

Text #4

Max Range: 0.9147. Min Range: -0.9147

Max Act: 0.7303. Min Act: -0.0001

Data Index: 252868 (C4 (Web Text))

Max Activating Token Index: 551

Text #5

Max Range: 0.9147. Min Range: -0.9147

Max Act: 0.6502. Min Act: -0.0001

Data Index: 987258 (C4 (Web Text))

Max Activating Token Index: 749

Text #6

Max Range: 0.9147. Min Range: -0.9147

Max Act: 0.7651. Min Act: -0.0001

Data Index: 1539763 (Python Code)

Max Activating Token Index: 786

Text #7

Max Range: 0.9147. Min Range: -0.9147

Max Act: 0.6869. Min Act: -0.0001

Data Index: 1396206 (Python Code)

Max Activating Token Index: 535

Text #8

Max Range: 0.9147. Min Range: -0.9147

Max Act: 0.6578. Min Act: -0.0001

Data Index: 233586 (C4 (Web Text))

Max Activating Token Index: 991

Text #9

Max Range: 0.9147. Min Range: -0.9147

Max Act: 0.6959. Min Act: -0.0001

Data Index: 1469329 (Python Code)

Max Activating Token Index: 802

Text #10

Max Range: 0.9147. Min Range: -0.9147

Max Act: 0.6989. Min Act: -0.0001

Data Index: 1351177 (C4 (Web Text))

Max Activating Token Index: 867

Text #11

Max Range: 0.9147. Min Range: -0.9147

Max Act: 0.6716. Min Act: -0.0001

Data Index: 1005152 (C4 (Web Text))

Max Activating Token Index: 222

Text #12

Max Range: 0.9147. Min Range: -0.9147

Max Act: 0.6706. Min Act: -0.0001

Data Index: 525852 (C4 (Web Text))

Max Activating Token Index: 469

Text #13

Max Range: 0.9147. Min Range: -0.9147

Max Act: 0.6703. Min Act: -0.0001

Data Index: 275742 (C4 (Web Text))

Max Activating Token Index: 53

Text #14

Max Range: 0.9147. Min Range: -0.9147

Max Act: 0.6889. Min Act: -0.0001

Data Index: 919484 (C4 (Web Text))

Max Activating Token Index: 746

Text #15

Max Range: 0.9147. Min Range: -0.9147

Max Act: 0.6402. Min Act: -0.0001

Data Index: 884940 (C4 (Web Text))

Max Activating Token Index: 822

Text #16

Max Range: 0.9147. Min Range: -0.9147

Max Act: 0.6553. Min Act: -0.0001

Data Index: 1004413 (C4 (Web Text))

Max Activating Token Index: 393

Text #17

Max Range: 0.9147. Min Range: -0.9147

Max Act: 0.6368. Min Act: -0.0001

Data Index: 945335 (C4 (Web Text))

Max Activating Token Index: 998

Text #18

Max Range: 0.9147. Min Range: -0.9147

Max Act: 0.6764. Min Act: -0.0001

Data Index: 142484 (C4 (Web Text))

Max Activating Token Index: 338

Text #19

Max Range: 0.9147. Min Range: -0.9147

Max Act: 0.6322. Min Act: -0.0001

Data Index: 126904 (C4 (Web Text))

Max Activating Token Index: 650