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

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

Neuron 2036 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8539. Min Range: -1.8539

Max Act: 1.8539. Min Act: -0.0001

Data Index: 393771 (C4 (Web Text))

Max Activating Token Index: 313

Text #1

Max Range: 1.8539. Min Range: -1.8539

Max Act: 1.5680. Min Act: -0.0001

Data Index: 297847 (C4 (Web Text))

Max Activating Token Index: 749

Text #2

Max Range: 1.8539. Min Range: -1.8539

Max Act: 1.6480. Min Act: -0.0001

Data Index: 660462 (C4 (Web Text))

Max Activating Token Index: 27

Text #3

Max Range: 1.8539. Min Range: -1.8539

Max Act: 1.4916. Min Act: -0.0001

Data Index: 879874 (C4 (Web Text))

Max Activating Token Index: 1014

Text #4

Max Range: 1.8539. Min Range: -1.8539

Max Act: 1.2844. Min Act: -0.0001

Data Index: 360178 (C4 (Web Text))

Max Activating Token Index: 1017

Text #5

Max Range: 1.8539. Min Range: -1.8539

Max Act: 1.2044. Min Act: -0.0001

Data Index: 424226 (C4 (Web Text))

Max Activating Token Index: 864

Text #6

Max Range: 1.8539. Min Range: -1.8539

Max Act: 1.2736. Min Act: -0.0001

Data Index: 986339 (C4 (Web Text))

Max Activating Token Index: 214

Text #7

Max Range: 1.8539. Min Range: -1.8539

Max Act: 1.0559. Min Act: -0.0001

Data Index: 108818 (C4 (Web Text))

Max Activating Token Index: 712

Text #8

Max Range: 1.8539. Min Range: -1.8539

Max Act: 1.0209. Min Act: -0.0001

Data Index: 1123907 (C4 (Web Text))

Max Activating Token Index: 46

Text #9

Max Range: 1.8539. Min Range: -1.8539

Max Act: 0.9494. Min Act: -0.0001

Data Index: 263119 (C4 (Web Text))

Max Activating Token Index: 784

Text #10

Max Range: 1.8539. Min Range: -1.8539

Max Act: 0.9336. Min Act: -0.0001

Data Index: 693821 (C4 (Web Text))

Max Activating Token Index: 59

Text #11

Max Range: 1.8539. Min Range: -1.8539

Max Act: 0.8524. Min Act: -0.0001

Data Index: 559274 (C4 (Web Text))

Max Activating Token Index: 284

Text #12

Max Range: 1.8539. Min Range: -1.8539

Max Act: 0.8171. Min Act: -0.0001

Data Index: 891737 (C4 (Web Text))

Max Activating Token Index: 611

Text #13

Max Range: 1.8539. Min Range: -1.8539

Max Act: 0.8770. Min Act: -0.0001

Data Index: 250070 (C4 (Web Text))

Max Activating Token Index: 99

Text #14

Max Range: 1.8539. Min Range: -1.8539

Max Act: 0.8387. Min Act: -0.0001

Data Index: 1134650 (C4 (Web Text))

Max Activating Token Index: 566

Text #15

Max Range: 1.8539. Min Range: -1.8539

Max Act: 0.8590. Min Act: -0.0001

Data Index: 313129 (C4 (Web Text))

Max Activating Token Index: 96

Text #16

Max Range: 1.8539. Min Range: -1.8539

Max Act: 0.8798. Min Act: -0.0001

Data Index: 698771 (C4 (Web Text))

Max Activating Token Index: 100

Text #17

Max Range: 1.8539. Min Range: -1.8539

Max Act: 0.8490. Min Act: -0.0001

Data Index: 499222 (C4 (Web Text))

Max Activating Token Index: 35

Text #18

Max Range: 1.8539. Min Range: -1.8539

Max Act: 0.6850. Min Act: -0.0001

Data Index: 309603 (C4 (Web Text))

Max Activating Token Index: 736

Text #19

Max Range: 1.8539. Min Range: -1.8539

Max Act: 1.0365. Min Act: -0.0001

Data Index: 232639 (C4 (Web Text))

Max Activating Token Index: 736