Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4524 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.0510. Min Range: -1.0510

Max Act: 1.0510. Min Act: -0.0000

Data Index: 1060726 (C4 (Web Text))

Max Activating Token Index: 988

Text #1

Max Range: 1.0510. Min Range: -1.0510

Max Act: 0.9893. Min Act: -0.0000

Data Index: 770449 (C4 (Web Text))

Max Activating Token Index: 136

Text #2

Max Range: 1.0510. Min Range: -1.0510

Max Act: 0.9872. Min Act: -0.0000

Data Index: 904692 (C4 (Web Text))

Max Activating Token Index: 392

Text #3

Max Range: 1.0510. Min Range: -1.0510

Max Act: 0.9680. Min Act: 0.0003

Data Index: 813187 (C4 (Web Text))

Max Activating Token Index: 615

Text #4

Max Range: 1.0510. Min Range: -1.0510

Max Act: 0.9921. Min Act: -0.0000

Data Index: 944129 (C4 (Web Text))

Max Activating Token Index: 893

Text #5

Max Range: 1.0510. Min Range: -1.0510

Max Act: 0.9886. Min Act: -0.0000

Data Index: 961098 (C4 (Web Text))

Max Activating Token Index: 871

Text #6

Max Range: 1.0510. Min Range: -1.0510

Max Act: 0.9573. Min Act: -0.0000

Data Index: 1027112 (C4 (Web Text))

Max Activating Token Index: 80

Text #7

Max Range: 1.0510. Min Range: -1.0510

Max Act: 1.0114. Min Act: -0.0000

Data Index: 1105634 (C4 (Web Text))

Max Activating Token Index: 215

Text #8

Max Range: 1.0510. Min Range: -1.0510

Max Act: 1.0435. Min Act: -0.0000

Data Index: 120667 (C4 (Web Text))

Max Activating Token Index: 58

Text #9

Max Range: 1.0510. Min Range: -1.0510

Max Act: 0.9671. Min Act: -0.0000

Data Index: 323489 (C4 (Web Text))

Max Activating Token Index: 538

Text #10

Max Range: 1.0510. Min Range: -1.0510

Max Act: 0.9979. Min Act: 0.0001

Data Index: 817678 (C4 (Web Text))

Max Activating Token Index: 407

Text #11

Max Range: 1.0510. Min Range: -1.0510

Max Act: 0.9530. Min Act: -0.0000

Data Index: 897395 (C4 (Web Text))

Max Activating Token Index: 801

Text #12

Max Range: 1.0510. Min Range: -1.0510

Max Act: 0.9489. Min Act: -0.0000

Data Index: 216080 (C4 (Web Text))

Max Activating Token Index: 403

Text #13

Max Range: 1.0510. Min Range: -1.0510

Max Act: 0.9472. Min Act: -0.0000

Data Index: 261530 (C4 (Web Text))

Max Activating Token Index: 314

Text #14

Max Range: 1.0510. Min Range: -1.0510

Max Act: 0.9317. Min Act: -0.0000

Data Index: 1225078 (C4 (Web Text))

Max Activating Token Index: 288

Text #15

Max Range: 1.0510. Min Range: -1.0510

Max Act: 0.9254. Min Act: -0.0000

Data Index: 849452 (C4 (Web Text))

Max Activating Token Index: 29

Text #16

Max Range: 1.0510. Min Range: -1.0510

Max Act: 0.8703. Min Act: 0.0001

Data Index: 546510 (C4 (Web Text))

Max Activating Token Index: 685

Text #17

Max Range: 1.0510. Min Range: -1.0510

Max Act: 0.9737. Min Act: -0.0000

Data Index: 121116 (C4 (Web Text))

Max Activating Token Index: 461

Text #18

Max Range: 1.0510. Min Range: -1.0510

Max Act: 0.9137. Min Act: -0.0000

Data Index: 85278 (C4 (Web Text))

Max Activating Token Index: 140

Text #19

Max Range: 1.0510. Min Range: -1.0510

Max Act: 0.9495. Min Act: -0.0000

Data Index: 323214 (C4 (Web Text))

Max Activating Token Index: 367