Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3850 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.1749. Min Range: -2.1749

Max Act: 2.1749. Min Act: -0.0000

Data Index: 198513 (C4 (Web Text))

Max Activating Token Index: 71

Text #1

Max Range: 2.1749. Min Range: -2.1749

Max Act: 1.6178. Min Act: -0.0000

Data Index: 512758 (C4 (Web Text))

Max Activating Token Index: 68

Text #2

Max Range: 2.1749. Min Range: -2.1749

Max Act: 1.5720. Min Act: -0.0000

Data Index: 191792 (C4 (Web Text))

Max Activating Token Index: 109

Text #3

Max Range: 2.1749. Min Range: -2.1749

Max Act: 1.4449. Min Act: -0.0000

Data Index: 1207328 (C4 (Web Text))

Max Activating Token Index: 1002

Text #4

Max Range: 2.1749. Min Range: -2.1749

Max Act: 1.1346. Min Act: 0.0000

Data Index: 745589 (C4 (Web Text))

Max Activating Token Index: 74

Text #5

Max Range: 2.1749. Min Range: -2.1749

Max Act: 1.0539. Min Act: -0.0000

Data Index: 629539 (C4 (Web Text))

Max Activating Token Index: 871

Text #6

Max Range: 2.1749. Min Range: -2.1749

Max Act: 1.0651. Min Act: -0.0000

Data Index: 479384 (C4 (Web Text))

Max Activating Token Index: 203

Text #7

Max Range: 2.1749. Min Range: -2.1749

Max Act: 1.0729. Min Act: -0.0000

Data Index: 421747 (C4 (Web Text))

Max Activating Token Index: 750

Text #8

Max Range: 2.1749. Min Range: -2.1749

Max Act: 1.0526. Min Act: -0.0000

Data Index: 927864 (C4 (Web Text))

Max Activating Token Index: 201

Text #9

Max Range: 2.1749. Min Range: -2.1749

Max Act: 0.9650. Min Act: -0.0000

Data Index: 471859 (C4 (Web Text))

Max Activating Token Index: 870

Text #10

Max Range: 2.1749. Min Range: -2.1749

Max Act: 0.8989. Min Act: -0.0000

Data Index: 1262252 (C4 (Web Text))

Max Activating Token Index: 738

Text #11

Max Range: 2.1749. Min Range: -2.1749

Max Act: 0.8611. Min Act: -0.0000

Data Index: 46828 (C4 (Web Text))

Max Activating Token Index: 95

Text #12

Max Range: 2.1749. Min Range: -2.1749

Max Act: 0.8958. Min Act: -0.0000

Data Index: 1226155 (C4 (Web Text))

Max Activating Token Index: 982

Text #13

Max Range: 2.1749. Min Range: -2.1749

Max Act: 0.8388. Min Act: -0.0000

Data Index: 263900 (C4 (Web Text))

Max Activating Token Index: 620

Text #14

Max Range: 2.1749. Min Range: -2.1749

Max Act: 0.8547. Min Act: -0.0000

Data Index: 753030 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 2.1749. Min Range: -2.1749

Max Act: 0.8953. Min Act: -0.0000

Data Index: 333168 (C4 (Web Text))

Max Activating Token Index: 353

Text #16

Max Range: 2.1749. Min Range: -2.1749

Max Act: 0.8269. Min Act: -0.0000

Data Index: 654160 (C4 (Web Text))

Max Activating Token Index: 643

Text #17

Max Range: 2.1749. Min Range: -2.1749

Max Act: 0.8685. Min Act: -0.0000

Data Index: 923034 (C4 (Web Text))

Max Activating Token Index: 514

Text #18

Max Range: 2.1749. Min Range: -2.1749

Max Act: 0.8410. Min Act: -0.0000

Data Index: 1051969 (C4 (Web Text))

Max Activating Token Index: 240

Text #19

Max Range: 2.1749. Min Range: -2.1749

Max Act: 0.8154. Min Act: -0.0000

Data Index: 1303595 (C4 (Web Text))

Max Activating Token Index: 112