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

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

Neuron 282 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0802. Min Range: -1.0802

Max Act: 1.0802. Min Act: -0.0003

Data Index: 1033222 (C4 (Web Text))

Max Activating Token Index: 212

Text #1

Max Range: 1.0802. Min Range: -1.0802

Max Act: 0.9375. Min Act: -0.0003

Data Index: 247154 (C4 (Web Text))

Max Activating Token Index: 510

Text #2

Max Range: 1.0802. Min Range: -1.0802

Max Act: 1.0508. Min Act: -0.0003

Data Index: 582530 (C4 (Web Text))

Max Activating Token Index: 663

Text #3

Max Range: 1.0802. Min Range: -1.0802

Max Act: 1.0142. Min Act: -0.0003

Data Index: 1145966 (C4 (Web Text))

Max Activating Token Index: 447

Text #4

Max Range: 1.0802. Min Range: -1.0802

Max Act: 1.0000. Min Act: -0.0002

Data Index: 6464 (C4 (Web Text))

Max Activating Token Index: 112

Text #5

Max Range: 1.0802. Min Range: -1.0802

Max Act: 0.9385. Min Act: -0.0003

Data Index: 566805 (C4 (Web Text))

Max Activating Token Index: 390

Text #6

Max Range: 1.0802. Min Range: -1.0802

Max Act: 0.9299. Min Act: -0.0002

Data Index: 1148828 (C4 (Web Text))

Max Activating Token Index: 615

Text #7

Max Range: 1.0802. Min Range: -1.0802

Max Act: 1.0005. Min Act: -0.0002

Data Index: 468884 (C4 (Web Text))

Max Activating Token Index: 68

Text #8

Max Range: 1.0802. Min Range: -1.0802

Max Act: 0.9731. Min Act: -0.0003

Data Index: 1104321 (C4 (Web Text))

Max Activating Token Index: 449

Text #9

Max Range: 1.0802. Min Range: -1.0802

Max Act: 0.8092. Min Act: -0.0002

Data Index: 1098079 (C4 (Web Text))

Max Activating Token Index: 143

Text #10

Max Range: 1.0802. Min Range: -1.0802

Max Act: 0.9691. Min Act: -0.0002

Data Index: 639340 (C4 (Web Text))

Max Activating Token Index: 171

Text #11

Max Range: 1.0802. Min Range: -1.0802

Max Act: 0.8992. Min Act: -0.0003

Data Index: 655179 (C4 (Web Text))

Max Activating Token Index: 198

Text #12

Max Range: 1.0802. Min Range: -1.0802

Max Act: 1.0379. Min Act: -0.0003

Data Index: 304708 (C4 (Web Text))

Max Activating Token Index: 281

Text #13

Max Range: 1.0802. Min Range: -1.0802

Max Act: 0.8843. Min Act: -0.0002

Data Index: 1351715 (C4 (Web Text))

Max Activating Token Index: 432

Text #14

Max Range: 1.0802. Min Range: -1.0802

Max Act: 0.8732. Min Act: -0.0003

Data Index: 271926 (C4 (Web Text))

Max Activating Token Index: 13

Text #15

Max Range: 1.0802. Min Range: -1.0802

Max Act: 0.8851. Min Act: -0.0003

Data Index: 888338 (C4 (Web Text))

Max Activating Token Index: 316

Text #16

Max Range: 1.0802. Min Range: -1.0802

Max Act: 0.9323. Min Act: -0.0003

Data Index: 1105047 (C4 (Web Text))

Max Activating Token Index: 611

Text #17

Max Range: 1.0802. Min Range: -1.0802

Max Act: 0.8996. Min Act: -0.0003

Data Index: 773214 (C4 (Web Text))

Max Activating Token Index: 266

Text #18

Max Range: 1.0802. Min Range: -1.0802

Max Act: 0.7925. Min Act: -0.0003

Data Index: 24003 (C4 (Web Text))

Max Activating Token Index: 173

Text #19

Max Range: 1.0802. Min Range: -1.0802

Max Act: 0.8968. Min Act: -0.0002

Data Index: 257223 (C4 (Web Text))

Max Activating Token Index: 866