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

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

Neuron 3142 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1050. Min Range: -0.1050

Max Act: 0.1050. Min Act: -0.0001

Data Index: 566401 (C4 (Web Text))

Max Activating Token Index: 513

Text #1

Max Range: 0.1050. Min Range: -0.1050

Max Act: 0.0860. Min Act: -0.0001

Data Index: 1206080 (C4 (Web Text))

Max Activating Token Index: 783

Text #2

Max Range: 0.1050. Min Range: -0.1050

Max Act: 0.0935. Min Act: -0.0001

Data Index: 642417 (C4 (Web Text))

Max Activating Token Index: 358

Text #3

Max Range: 0.1050. Min Range: -0.1050

Max Act: 0.0877. Min Act: -0.0001

Data Index: 265912 (C4 (Web Text))

Max Activating Token Index: 917

Text #4

Max Range: 0.1050. Min Range: -0.1050

Max Act: 0.0846. Min Act: -0.0001

Data Index: 429452 (C4 (Web Text))

Max Activating Token Index: 202

Text #5

Max Range: 0.1050. Min Range: -0.1050

Max Act: 0.0755. Min Act: -0.0001

Data Index: 227530 (C4 (Web Text))

Max Activating Token Index: 459

Text #6

Max Range: 0.1050. Min Range: -0.1050

Max Act: 0.0725. Min Act: -0.0001

Data Index: 1636800 (Python Code)

Max Activating Token Index: 939

Text #7

Max Range: 0.1050. Min Range: -0.1050

Max Act: 0.0752. Min Act: -0.0001

Data Index: 3135 (C4 (Web Text))

Max Activating Token Index: 586

Text #8

Max Range: 0.1050. Min Range: -0.1050

Max Act: 0.0708. Min Act: -0.0001

Data Index: 1422218 (Python Code)

Max Activating Token Index: 828

Text #9

Max Range: 0.1050. Min Range: -0.1050

Max Act: 0.0709. Min Act: -0.0001

Data Index: 501595 (C4 (Web Text))

Max Activating Token Index: 448

Text #10

Max Range: 0.1050. Min Range: -0.1050

Max Act: 0.0701. Min Act: -0.0001

Data Index: 498683 (C4 (Web Text))

Max Activating Token Index: 236

Text #11

Max Range: 0.1050. Min Range: -0.1050

Max Act: 0.0667. Min Act: -0.0001

Data Index: 1634103 (Python Code)

Max Activating Token Index: 987

Text #12

Max Range: 0.1050. Min Range: -0.1050

Max Act: 0.0695. Min Act: -0.0001

Data Index: 1355798 (C4 (Web Text))

Max Activating Token Index: 84

Text #13

Max Range: 0.1050. Min Range: -0.1050

Max Act: 0.0661. Min Act: -0.0001

Data Index: 1544305 (Python Code)

Max Activating Token Index: 884

Text #14

Max Range: 0.1050. Min Range: -0.1050

Max Act: 0.0665. Min Act: -0.0001

Data Index: 1484247 (Python Code)

Max Activating Token Index: 288

Text #15

Max Range: 0.1050. Min Range: -0.1050

Max Act: 0.0692. Min Act: -0.0001

Data Index: 719324 (C4 (Web Text))

Max Activating Token Index: 55

Text #16

Max Range: 0.1050. Min Range: -0.1050

Max Act: 0.0659. Min Act: -0.0001

Data Index: 1426547 (Python Code)

Max Activating Token Index: 739

Text #17

Max Range: 0.1050. Min Range: -0.1050

Max Act: 0.0612. Min Act: -0.0001

Data Index: 1466276 (Python Code)

Max Activating Token Index: 814

Text #18

Max Range: 0.1050. Min Range: -0.1050

Max Act: 0.0631. Min Act: -0.0001

Data Index: 426212 (C4 (Web Text))

Max Activating Token Index: 629

Text #19

Max Range: 0.1050. Min Range: -0.1050

Max Act: 0.0645. Min Act: -0.0001

Data Index: 800817 (C4 (Web Text))

Max Activating Token Index: 124