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

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

Neuron 1133 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: 7.9035. Min Range: -7.9035

Max Act: 7.9035. Min Act: -0.0001

Data Index: 904544 (C4 (Web Text))

Max Activating Token Index: 661

Text #1

Max Range: 7.9035. Min Range: -7.9035

Max Act: 7.2689. Min Act: -0.0001

Data Index: 944517 (C4 (Web Text))

Max Activating Token Index: 199

Text #2

Max Range: 7.9035. Min Range: -7.9035

Max Act: 7.2522. Min Act: -0.0001

Data Index: 623207 (C4 (Web Text))

Max Activating Token Index: 772

Text #3

Max Range: 7.9035. Min Range: -7.9035

Max Act: 6.9515. Min Act: -0.0001

Data Index: 573301 (C4 (Web Text))

Max Activating Token Index: 341

Text #4

Max Range: 7.9035. Min Range: -7.9035

Max Act: 7.0603. Min Act: -0.0001

Data Index: 1353736 (C4 (Web Text))

Max Activating Token Index: 85

Text #5

Max Range: 7.9035. Min Range: -7.9035

Max Act: 6.8605. Min Act: -0.0001

Data Index: 998142 (C4 (Web Text))

Max Activating Token Index: 388

Text #6

Max Range: 7.9035. Min Range: -7.9035

Max Act: 6.8667. Min Act: -0.0001

Data Index: 329705 (C4 (Web Text))

Max Activating Token Index: 500

Text #7

Max Range: 7.9035. Min Range: -7.9035

Max Act: 6.8614. Min Act: -0.0001

Data Index: 1050977 (C4 (Web Text))

Max Activating Token Index: 453

Text #8

Max Range: 7.9035. Min Range: -7.9035

Max Act: 6.7766. Min Act: -0.0001

Data Index: 353850 (C4 (Web Text))

Max Activating Token Index: 141

Text #9

Max Range: 7.9035. Min Range: -7.9035

Max Act: 6.5810. Min Act: -0.0001

Data Index: 612078 (C4 (Web Text))

Max Activating Token Index: 612

Text #10

Max Range: 7.9035. Min Range: -7.9035

Max Act: 6.7166. Min Act: -0.0001

Data Index: 534942 (C4 (Web Text))

Max Activating Token Index: 867

Text #11

Max Range: 7.9035. Min Range: -7.9035

Max Act: 6.7107. Min Act: -0.0001

Data Index: 343101 (C4 (Web Text))

Max Activating Token Index: 234

Text #12

Max Range: 7.9035. Min Range: -7.9035

Max Act: 6.6789. Min Act: -0.0001

Data Index: 1353856 (C4 (Web Text))

Max Activating Token Index: 408

Text #13

Max Range: 7.9035. Min Range: -7.9035

Max Act: 6.6254. Min Act: -0.0001

Data Index: 426635 (C4 (Web Text))

Max Activating Token Index: 418

Text #14

Max Range: 7.9035. Min Range: -7.9035

Max Act: 6.7794. Min Act: -0.0001

Data Index: 700217 (C4 (Web Text))

Max Activating Token Index: 287

Text #15

Max Range: 7.9035. Min Range: -7.9035

Max Act: 6.4096. Min Act: -0.0001

Data Index: 1008938 (C4 (Web Text))

Max Activating Token Index: 316

Text #16

Max Range: 7.9035. Min Range: -7.9035

Max Act: 6.5369. Min Act: -0.0001

Data Index: 463464 (C4 (Web Text))

Max Activating Token Index: 602

Text #17

Max Range: 7.9035. Min Range: -7.9035

Max Act: 6.5648. Min Act: -0.0001

Data Index: 91820 (C4 (Web Text))

Max Activating Token Index: 374

Text #18

Max Range: 7.9035. Min Range: -7.9035

Max Act: 6.3814. Min Act: -0.0001

Data Index: 1167969 (C4 (Web Text))

Max Activating Token Index: 696

Text #19

Max Range: 7.9035. Min Range: -7.9035

Max Act: 6.5221. Min Act: -0.0001

Data Index: 1198141 (C4 (Web Text))

Max Activating Token Index: 441