Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 812 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.4256. Min Range: -0.4256

Max Act: 0.4256. Min Act: -0.0003

Data Index: 77569 (C4 (Web Text))

Max Activating Token Index: 985

Text #1

Max Range: 0.4256. Min Range: -0.4256

Max Act: 0.3832. Min Act: -0.0003

Data Index: 1216133 (C4 (Web Text))

Max Activating Token Index: 521

Text #2

Max Range: 0.4256. Min Range: -0.4256

Max Act: 0.3752. Min Act: -0.0003

Data Index: 959753 (C4 (Web Text))

Max Activating Token Index: 451

Text #3

Max Range: 0.4256. Min Range: -0.4256

Max Act: 0.2062. Min Act: -0.0003

Data Index: 523705 (C4 (Web Text))

Max Activating Token Index: 592

Text #4

Max Range: 0.4256. Min Range: -0.4256

Max Act: 0.3548. Min Act: -0.0003

Data Index: 159537 (C4 (Web Text))

Max Activating Token Index: 455

Text #5

Max Range: 0.4256. Min Range: -0.4256

Max Act: 0.3624. Min Act: -0.0003

Data Index: 972474 (C4 (Web Text))

Max Activating Token Index: 662

Text #6

Max Range: 0.4256. Min Range: -0.4256

Max Act: 0.3550. Min Act: -0.0003

Data Index: 641684 (C4 (Web Text))

Max Activating Token Index: 561

Text #7

Max Range: 0.4256. Min Range: -0.4256

Max Act: 0.3323. Min Act: -0.0003

Data Index: 1082564 (C4 (Web Text))

Max Activating Token Index: 529

Text #8

Max Range: 0.4256. Min Range: -0.4256

Max Act: 0.3364. Min Act: -0.0003

Data Index: 486822 (C4 (Web Text))

Max Activating Token Index: 303

Text #9

Max Range: 0.4256. Min Range: -0.4256

Max Act: 0.3355. Min Act: -0.0003

Data Index: 846288 (C4 (Web Text))

Max Activating Token Index: 845

Text #10

Max Range: 0.4256. Min Range: -0.4256

Max Act: 0.3396. Min Act: -0.0003

Data Index: 723571 (C4 (Web Text))

Max Activating Token Index: 411

Text #11

Max Range: 0.4256. Min Range: -0.4256

Max Act: 0.3325. Min Act: -0.0003

Data Index: 312217 (C4 (Web Text))

Max Activating Token Index: 525

Text #12

Max Range: 0.4256. Min Range: -0.4256

Max Act: 0.3343. Min Act: -0.0003

Data Index: 1022967 (C4 (Web Text))

Max Activating Token Index: 774

Text #13

Max Range: 0.4256. Min Range: -0.4256

Max Act: 0.3136. Min Act: -0.0003

Data Index: 80054 (C4 (Web Text))

Max Activating Token Index: 383

Text #14

Max Range: 0.4256. Min Range: -0.4256

Max Act: 0.3111. Min Act: -0.0003

Data Index: 123370 (C4 (Web Text))

Max Activating Token Index: 66

Text #15

Max Range: 0.4256. Min Range: -0.4256

Max Act: 0.2960. Min Act: -0.0003

Data Index: 1333173 (C4 (Web Text))

Max Activating Token Index: 921

Text #16

Max Range: 0.4256. Min Range: -0.4256

Max Act: 0.2950. Min Act: -0.0003

Data Index: 441955 (C4 (Web Text))

Max Activating Token Index: 686

Text #17

Max Range: 0.4256. Min Range: -0.4256

Max Act: 0.3148. Min Act: -0.0003

Data Index: 568141 (C4 (Web Text))

Max Activating Token Index: 600

Text #18

Max Range: 0.4256. Min Range: -0.4256

Max Act: 0.3026. Min Act: -0.0003

Data Index: 1221356 (C4 (Web Text))

Max Activating Token Index: 152

Text #19

Max Range: 0.4256. Min Range: -0.4256

Max Act: 0.2814. Min Act: -0.0003

Data Index: 579152 (C4 (Web Text))

Max Activating Token Index: 197