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

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

Neuron 4902 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: 0.7028. Min Range: -0.7028

Max Act: 0.7028. Min Act: -0.0000

Data Index: 726519 (C4 (Web Text))

Max Activating Token Index: 785

Text #1

Max Range: 0.7028. Min Range: -0.7028

Max Act: 0.6033. Min Act: -0.0000

Data Index: 633111 (C4 (Web Text))

Max Activating Token Index: 761

Text #2

Max Range: 0.7028. Min Range: -0.7028

Max Act: 0.4621. Min Act: -0.0000

Data Index: 1353468 (C4 (Web Text))

Max Activating Token Index: 331

Text #3

Max Range: 0.7028. Min Range: -0.7028

Max Act: 0.4689. Min Act: -0.0000

Data Index: 820454 (C4 (Web Text))

Max Activating Token Index: 750

Text #4

Max Range: 0.7028. Min Range: -0.7028

Max Act: 0.4372. Min Act: -0.0000

Data Index: 590036 (C4 (Web Text))

Max Activating Token Index: 794

Text #5

Max Range: 0.7028. Min Range: -0.7028

Max Act: 0.4067. Min Act: -0.0000

Data Index: 832826 (C4 (Web Text))

Max Activating Token Index: 488

Text #6

Max Range: 0.7028. Min Range: -0.7028

Max Act: 0.4157. Min Act: -0.0000

Data Index: 1240816 (C4 (Web Text))

Max Activating Token Index: 991

Text #7

Max Range: 0.7028. Min Range: -0.7028

Max Act: 0.3636. Min Act: -0.0000

Data Index: 313874 (C4 (Web Text))

Max Activating Token Index: 495

Text #8

Max Range: 0.7028. Min Range: -0.7028

Max Act: 0.4135. Min Act: -0.0000

Data Index: 1131424 (C4 (Web Text))

Max Activating Token Index: 264

Text #9

Max Range: 0.7028. Min Range: -0.7028

Max Act: 0.3572. Min Act: -0.0000

Data Index: 1063586 (C4 (Web Text))

Max Activating Token Index: 440

Text #10

Max Range: 0.7028. Min Range: -0.7028

Max Act: 0.4100. Min Act: -0.0000

Data Index: 1322500 (C4 (Web Text))

Max Activating Token Index: 775

Text #11

Max Range: 0.7028. Min Range: -0.7028

Max Act: 0.3524. Min Act: -0.0000

Data Index: 314456 (C4 (Web Text))

Max Activating Token Index: 272

Text #12

Max Range: 0.7028. Min Range: -0.7028

Max Act: 0.3653. Min Act: -0.0000

Data Index: 369424 (C4 (Web Text))

Max Activating Token Index: 532

Text #13

Max Range: 0.7028. Min Range: -0.7028

Max Act: 0.3497. Min Act: -0.0000

Data Index: 800084 (C4 (Web Text))

Max Activating Token Index: 246

Text #14

Max Range: 0.7028. Min Range: -0.7028

Max Act: 0.3454. Min Act: -0.0000

Data Index: 853294 (C4 (Web Text))

Max Activating Token Index: 269

Text #15

Max Range: 0.7028. Min Range: -0.7028

Max Act: 0.3200. Min Act: -0.0000

Data Index: 901754 (C4 (Web Text))

Max Activating Token Index: 314

Text #16

Max Range: 0.7028. Min Range: -0.7028

Max Act: 0.3446. Min Act: -0.0000

Data Index: 78217 (C4 (Web Text))

Max Activating Token Index: 56

Text #17

Max Range: 0.7028. Min Range: -0.7028

Max Act: 0.3228. Min Act: -0.0000

Data Index: 202946 (C4 (Web Text))

Max Activating Token Index: 981

Text #18

Max Range: 0.7028. Min Range: -0.7028

Max Act: 0.3274. Min Act: -0.0000

Data Index: 781164 (C4 (Web Text))

Max Activating Token Index: 443

Text #19

Max Range: 0.7028. Min Range: -0.7028

Max Act: 0.3293. Min Act: -0.0000

Data Index: 268338 (C4 (Web Text))

Max Activating Token Index: 191