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

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

Neuron 3787 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1518. Min Range: -3.1518

Max Act: 3.1518. Min Act: -0.0000

Data Index: 790905 (C4 (Web Text))

Max Activating Token Index: 889

Text #1

Max Range: 3.1518. Min Range: -3.1518

Max Act: 2.7628. Min Act: -0.0000

Data Index: 1085433 (C4 (Web Text))

Max Activating Token Index: 866

Text #2

Max Range: 3.1518. Min Range: -3.1518

Max Act: 2.6822. Min Act: -0.0000

Data Index: 896330 (C4 (Web Text))

Max Activating Token Index: 186

Text #3

Max Range: 3.1518. Min Range: -3.1518

Max Act: 2.4563. Min Act: -0.0000

Data Index: 982450 (C4 (Web Text))

Max Activating Token Index: 231

Text #4

Max Range: 3.1518. Min Range: -3.1518

Max Act: 2.5544. Min Act: -0.0000

Data Index: 374693 (C4 (Web Text))

Max Activating Token Index: 158

Text #5

Max Range: 3.1518. Min Range: -3.1518

Max Act: 2.3791. Min Act: -0.0000

Data Index: 402097 (C4 (Web Text))

Max Activating Token Index: 900

Text #6

Max Range: 3.1518. Min Range: -3.1518

Max Act: 2.3109. Min Act: -0.0000

Data Index: 867257 (C4 (Web Text))

Max Activating Token Index: 274

Text #7

Max Range: 3.1518. Min Range: -3.1518

Max Act: 2.4466. Min Act: -0.0000

Data Index: 476896 (C4 (Web Text))

Max Activating Token Index: 162

Text #8

Max Range: 3.1518. Min Range: -3.1518

Max Act: 2.4492. Min Act: -0.0000

Data Index: 844369 (C4 (Web Text))

Max Activating Token Index: 1013

Text #9

Max Range: 3.1518. Min Range: -3.1518

Max Act: 2.4098. Min Act: -0.0000

Data Index: 968003 (C4 (Web Text))

Max Activating Token Index: 955

Text #10

Max Range: 3.1518. Min Range: -3.1518

Max Act: 2.2749. Min Act: -0.0000

Data Index: 265912 (C4 (Web Text))

Max Activating Token Index: 88

Text #11

Max Range: 3.1518. Min Range: -3.1518

Max Act: 2.2789. Min Act: -0.0000

Data Index: 842960 (C4 (Web Text))

Max Activating Token Index: 653

Text #12

Max Range: 3.1518. Min Range: -3.1518

Max Act: 2.3880. Min Act: -0.0000

Data Index: 105642 (C4 (Web Text))

Max Activating Token Index: 276

Text #13

Max Range: 3.1518. Min Range: -3.1518

Max Act: 2.2526. Min Act: -0.0000

Data Index: 1104292 (C4 (Web Text))

Max Activating Token Index: 760

Text #14

Max Range: 3.1518. Min Range: -3.1518

Max Act: 2.3338. Min Act: -0.0000

Data Index: 555212 (C4 (Web Text))

Max Activating Token Index: 406

Text #15

Max Range: 3.1518. Min Range: -3.1518

Max Act: 2.4711. Min Act: -0.0000

Data Index: 1029420 (C4 (Web Text))

Max Activating Token Index: 1014

Text #16

Max Range: 3.1518. Min Range: -3.1518

Max Act: 2.4326. Min Act: -0.0000

Data Index: 514135 (C4 (Web Text))

Max Activating Token Index: 996

Text #17

Max Range: 3.1518. Min Range: -3.1518

Max Act: 2.3208. Min Act: -0.0000

Data Index: 525403 (C4 (Web Text))

Max Activating Token Index: 611

Text #18

Max Range: 3.1518. Min Range: -3.1518

Max Act: 2.2003. Min Act: -0.0000

Data Index: 938616 (C4 (Web Text))

Max Activating Token Index: 240

Text #19

Max Range: 3.1518. Min Range: -3.1518

Max Act: 2.1492. Min Act: -0.0000

Data Index: 962074 (C4 (Web Text))

Max Activating Token Index: 306