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

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

Neuron 1849 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8182. Min Range: -1.8182

Max Act: 1.7867. Min Act: -0.0001

Data Index: 623385 (C4 (Web Text))

Max Activating Token Index: 494

Text #1

Max Range: 1.8182. Min Range: -1.8182

Max Act: 1.8182. Min Act: -0.0001

Data Index: 608228 (C4 (Web Text))

Max Activating Token Index: 899

Text #2

Max Range: 1.8182. Min Range: -1.8182

Max Act: 1.6426. Min Act: -0.0001

Data Index: 1283483 (C4 (Web Text))

Max Activating Token Index: 78

Text #3

Max Range: 1.8182. Min Range: -1.8182

Max Act: 1.6856. Min Act: -0.0001

Data Index: 971822 (C4 (Web Text))

Max Activating Token Index: 917

Text #4

Max Range: 1.8182. Min Range: -1.8182

Max Act: 1.5997. Min Act: -0.0001

Data Index: 1608964 (Python Code)

Max Activating Token Index: 360

Text #5

Max Range: 1.8182. Min Range: -1.8182

Max Act: 1.5963. Min Act: -0.0001

Data Index: 995056 (C4 (Web Text))

Max Activating Token Index: 253

Text #6

Max Range: 1.8182. Min Range: -1.8182

Max Act: 1.4441. Min Act: -0.0001

Data Index: 1221047 (C4 (Web Text))

Max Activating Token Index: 595

Text #7

Max Range: 1.8182. Min Range: -1.8182

Max Act: 1.4634. Min Act: -0.0001

Data Index: 1200316 (C4 (Web Text))

Max Activating Token Index: 507

Text #8

Max Range: 1.8182. Min Range: -1.8182

Max Act: 1.5797. Min Act: -0.0001

Data Index: 308657 (C4 (Web Text))

Max Activating Token Index: 427

Text #9

Max Range: 1.8182. Min Range: -1.8182

Max Act: 1.4853. Min Act: -0.0001

Data Index: 1344136 (C4 (Web Text))

Max Activating Token Index: 575

Text #10

Max Range: 1.8182. Min Range: -1.8182

Max Act: 1.5682. Min Act: -0.0001

Data Index: 557435 (C4 (Web Text))

Max Activating Token Index: 90

Text #11

Max Range: 1.8182. Min Range: -1.8182

Max Act: 1.4608. Min Act: -0.0001

Data Index: 1408844 (Python Code)

Max Activating Token Index: 351

Text #12

Max Range: 1.8182. Min Range: -1.8182

Max Act: 1.5425. Min Act: -0.0001

Data Index: 1345583 (C4 (Web Text))

Max Activating Token Index: 977

Text #13

Max Range: 1.8182. Min Range: -1.8182

Max Act: 1.4898. Min Act: -0.0001

Data Index: 1257880 (C4 (Web Text))

Max Activating Token Index: 939

Text #14

Max Range: 1.8182. Min Range: -1.8182

Max Act: 1.4845. Min Act: -0.0001

Data Index: 250865 (C4 (Web Text))

Max Activating Token Index: 682

Text #15

Max Range: 1.8182. Min Range: -1.8182

Max Act: 1.5266. Min Act: -0.0001

Data Index: 248701 (C4 (Web Text))

Max Activating Token Index: 311

Text #16

Max Range: 1.8182. Min Range: -1.8182

Max Act: 1.4495. Min Act: -0.0001

Data Index: 962785 (C4 (Web Text))

Max Activating Token Index: 27

Text #17

Max Range: 1.8182. Min Range: -1.8182

Max Act: 1.4031. Min Act: -0.0001

Data Index: 1120083 (C4 (Web Text))

Max Activating Token Index: 798

Text #18

Max Range: 1.8182. Min Range: -1.8182

Max Act: 1.3932. Min Act: -0.0001

Data Index: 232365 (C4 (Web Text))

Max Activating Token Index: 459

Text #19

Max Range: 1.8182. Min Range: -1.8182

Max Act: 1.2682. Min Act: -0.0001

Data Index: 32261 (C4 (Web Text))

Max Activating Token Index: 922