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

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

Neuron 3082 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8467. Min Range: -0.8467

Max Act: 0.8467. Min Act: -0.0000

Data Index: 837786 (C4 (Web Text))

Max Activating Token Index: 1019

Text #1

Max Range: 0.8467. Min Range: -0.8467

Max Act: 0.8452. Min Act: -0.0001

Data Index: 184552 (C4 (Web Text))

Max Activating Token Index: 365

Text #2

Max Range: 0.8467. Min Range: -0.8467

Max Act: 0.7392. Min Act: -0.0000

Data Index: 419658 (C4 (Web Text))

Max Activating Token Index: 40

Text #3

Max Range: 0.8467. Min Range: -0.8467

Max Act: 0.6864. Min Act: -0.0000

Data Index: 367691 (C4 (Web Text))

Max Activating Token Index: 700

Text #4

Max Range: 0.8467. Min Range: -0.8467

Max Act: 0.6673. Min Act: -0.0000

Data Index: 642267 (C4 (Web Text))

Max Activating Token Index: 563

Text #5

Max Range: 0.8467. Min Range: -0.8467

Max Act: 0.7033. Min Act: -0.0001

Data Index: 1359011 (C4 (Web Text))

Max Activating Token Index: 933

Text #6

Max Range: 0.8467. Min Range: -0.8467

Max Act: 0.5986. Min Act: -0.0000

Data Index: 620114 (C4 (Web Text))

Max Activating Token Index: 617

Text #7

Max Range: 0.8467. Min Range: -0.8467

Max Act: 0.5905. Min Act: -0.0000

Data Index: 947124 (C4 (Web Text))

Max Activating Token Index: 323

Text #8

Max Range: 0.8467. Min Range: -0.8467

Max Act: 0.6115. Min Act: -0.0000

Data Index: 96129 (C4 (Web Text))

Max Activating Token Index: 437

Text #9

Max Range: 0.8467. Min Range: -0.8467

Max Act: 0.6287. Min Act: -0.0000

Data Index: 461571 (C4 (Web Text))

Max Activating Token Index: 395

Text #10

Max Range: 0.8467. Min Range: -0.8467

Max Act: 0.6104. Min Act: -0.0000

Data Index: 891985 (C4 (Web Text))

Max Activating Token Index: 428

Text #11

Max Range: 0.8467. Min Range: -0.8467

Max Act: 0.5758. Min Act: -0.0001

Data Index: 1293130 (C4 (Web Text))

Max Activating Token Index: 765

Text #12

Max Range: 0.8467. Min Range: -0.8467

Max Act: 0.5942. Min Act: -0.0000

Data Index: 637762 (C4 (Web Text))

Max Activating Token Index: 89

Text #13

Max Range: 0.8467. Min Range: -0.8467

Max Act: 0.5751. Min Act: -0.0000

Data Index: 785806 (C4 (Web Text))

Max Activating Token Index: 382

Text #14

Max Range: 0.8467. Min Range: -0.8467

Max Act: 0.5756. Min Act: -0.0000

Data Index: 442783 (C4 (Web Text))

Max Activating Token Index: 60

Text #15

Max Range: 0.8467. Min Range: -0.8467

Max Act: 0.5861. Min Act: -0.0000

Data Index: 849676 (C4 (Web Text))

Max Activating Token Index: 157

Text #16

Max Range: 0.8467. Min Range: -0.8467

Max Act: 0.5866. Min Act: -0.0000

Data Index: 1082005 (C4 (Web Text))

Max Activating Token Index: 140

Text #17

Max Range: 0.8467. Min Range: -0.8467

Max Act: 0.5799. Min Act: -0.0000

Data Index: 1013969 (C4 (Web Text))

Max Activating Token Index: 917

Text #18

Max Range: 0.8467. Min Range: -0.8467

Max Act: 0.5265. Min Act: -0.0000

Data Index: 1150085 (C4 (Web Text))

Max Activating Token Index: 57

Text #19

Max Range: 0.8467. Min Range: -0.8467

Max Act: 0.5593. Min Act: -0.0000

Data Index: 1118944 (C4 (Web Text))

Max Activating Token Index: 940