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

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

Neuron 530 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: 0.0123. Min Range: -0.0123

Max Act: 0.0121. Min Act: -0.0003

Data Index: 964048 (C4 (Web Text))

Max Activating Token Index: 622

Text #1

Max Range: 0.0123. Min Range: -0.0123

Max Act: 0.0113. Min Act: -0.0003

Data Index: 597090 (C4 (Web Text))

Max Activating Token Index: 458

Text #2

Max Range: 0.0123. Min Range: -0.0123

Max Act: 0.0123. Min Act: -0.0003

Data Index: 1016417 (C4 (Web Text))

Max Activating Token Index: 859

Text #3

Max Range: 0.0123. Min Range: -0.0123

Max Act: 0.0113. Min Act: -0.0002

Data Index: 1360069 (Python Code)

Max Activating Token Index: 157

Text #4

Max Range: 0.0123. Min Range: -0.0123

Max Act: 0.0109. Min Act: -0.0003

Data Index: 1280870 (C4 (Web Text))

Max Activating Token Index: 166

Text #5

Max Range: 0.0123. Min Range: -0.0123

Max Act: 0.0109. Min Act: -0.0003

Data Index: 1224340 (C4 (Web Text))

Max Activating Token Index: 82

Text #6

Max Range: 0.0123. Min Range: -0.0123

Max Act: 0.0108. Min Act: -0.0003

Data Index: 417626 (C4 (Web Text))

Max Activating Token Index: 967

Text #7

Max Range: 0.0123. Min Range: -0.0123

Max Act: 0.0106. Min Act: -0.0003

Data Index: 1052832 (C4 (Web Text))

Max Activating Token Index: 72

Text #8

Max Range: 0.0123. Min Range: -0.0123

Max Act: 0.0108. Min Act: -0.0003

Data Index: 847559 (C4 (Web Text))

Max Activating Token Index: 930

Text #9

Max Range: 0.0123. Min Range: -0.0123

Max Act: 0.0108. Min Act: -0.0003

Data Index: 242695 (C4 (Web Text))

Max Activating Token Index: 348

Text #10

Max Range: 0.0123. Min Range: -0.0123

Max Act: 0.0104. Min Act: -0.0003

Data Index: 148500 (C4 (Web Text))

Max Activating Token Index: 781

Text #11

Max Range: 0.0123. Min Range: -0.0123

Max Act: 0.0106. Min Act: -0.0003

Data Index: 818762 (C4 (Web Text))

Max Activating Token Index: 664

Text #12

Max Range: 0.0123. Min Range: -0.0123

Max Act: 0.0107. Min Act: -0.0003

Data Index: 222758 (C4 (Web Text))

Max Activating Token Index: 64

Text #13

Max Range: 0.0123. Min Range: -0.0123

Max Act: 0.0106. Min Act: -0.0003

Data Index: 475968 (C4 (Web Text))

Max Activating Token Index: 393

Text #14

Max Range: 0.0123. Min Range: -0.0123

Max Act: 0.0107. Min Act: -0.0003

Data Index: 588929 (C4 (Web Text))

Max Activating Token Index: 552

Text #15

Max Range: 0.0123. Min Range: -0.0123

Max Act: 0.0106. Min Act: -0.0003

Data Index: 187330 (C4 (Web Text))

Max Activating Token Index: 720

Text #16

Max Range: 0.0123. Min Range: -0.0123

Max Act: 0.0103. Min Act: -0.0003

Data Index: 1093117 (C4 (Web Text))

Max Activating Token Index: 167

Text #17

Max Range: 0.0123. Min Range: -0.0123

Max Act: 0.0096. Min Act: -0.0003

Data Index: 12619 (C4 (Web Text))

Max Activating Token Index: 833

Text #18

Max Range: 0.0123. Min Range: -0.0123

Max Act: 0.0104. Min Act: -0.0003

Data Index: 747223 (C4 (Web Text))

Max Activating Token Index: 782

Text #19

Max Range: 0.0123. Min Range: -0.0123

Max Act: 0.0103. Min Act: -0.0003

Data Index: 703057 (C4 (Web Text))

Max Activating Token Index: 765