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

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

Neuron 2363 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.5990. Min Range: -5.5990

Max Act: 5.5990. Min Act: -0.0000

Data Index: 1100498 (C4 (Web Text))

Max Activating Token Index: 133

Text #1

Max Range: 5.5990. Min Range: -5.5990

Max Act: 4.9593. Min Act: -0.0000

Data Index: 1153958 (C4 (Web Text))

Max Activating Token Index: 56

Text #2

Max Range: 5.5990. Min Range: -5.5990

Max Act: 5.2905. Min Act: -0.0000

Data Index: 1151742 (C4 (Web Text))

Max Activating Token Index: 643

Text #3

Max Range: 5.5990. Min Range: -5.5990

Max Act: 4.3609. Min Act: -0.0000

Data Index: 394553 (C4 (Web Text))

Max Activating Token Index: 895

Text #4

Max Range: 5.5990. Min Range: -5.5990

Max Act: 4.4448. Min Act: -0.0000

Data Index: 494421 (C4 (Web Text))

Max Activating Token Index: 546

Text #5

Max Range: 5.5990. Min Range: -5.5990

Max Act: 3.9274. Min Act: -0.0000

Data Index: 956704 (C4 (Web Text))

Max Activating Token Index: 156

Text #6

Max Range: 5.5990. Min Range: -5.5990

Max Act: 3.8877. Min Act: -0.0000

Data Index: 95490 (C4 (Web Text))

Max Activating Token Index: 1011

Text #7

Max Range: 5.5990. Min Range: -5.5990

Max Act: 3.6267. Min Act: -0.0000

Data Index: 797533 (C4 (Web Text))

Max Activating Token Index: 35

Text #8

Max Range: 5.5990. Min Range: -5.5990

Max Act: 3.7607. Min Act: -0.0000

Data Index: 514563 (C4 (Web Text))

Max Activating Token Index: 708

Text #9

Max Range: 5.5990. Min Range: -5.5990

Max Act: 3.5841. Min Act: -0.0000

Data Index: 1227667 (C4 (Web Text))

Max Activating Token Index: 286

Text #10

Max Range: 5.5990. Min Range: -5.5990

Max Act: 3.6444. Min Act: -0.0000

Data Index: 1134385 (C4 (Web Text))

Max Activating Token Index: 254

Text #11

Max Range: 5.5990. Min Range: -5.5990

Max Act: 3.6496. Min Act: -0.0000

Data Index: 487090 (C4 (Web Text))

Max Activating Token Index: 28

Text #12

Max Range: 5.5990. Min Range: -5.5990

Max Act: 2.9704. Min Act: -0.0000

Data Index: 1245494 (C4 (Web Text))

Max Activating Token Index: 414

Text #13

Max Range: 5.5990. Min Range: -5.5990

Max Act: 3.5146. Min Act: -0.0000

Data Index: 130982 (C4 (Web Text))

Max Activating Token Index: 948

Text #14

Max Range: 5.5990. Min Range: -5.5990

Max Act: 3.4950. Min Act: -0.0000

Data Index: 620825 (C4 (Web Text))

Max Activating Token Index: 881

Text #15

Max Range: 5.5990. Min Range: -5.5990

Max Act: 2.9213. Min Act: -0.0000

Data Index: 678094 (C4 (Web Text))

Max Activating Token Index: 848

Text #16

Max Range: 5.5990. Min Range: -5.5990

Max Act: 3.0724. Min Act: -0.0000

Data Index: 1136955 (C4 (Web Text))

Max Activating Token Index: 860

Text #17

Max Range: 5.5990. Min Range: -5.5990

Max Act: 3.4558. Min Act: -0.0000

Data Index: 18776 (C4 (Web Text))

Max Activating Token Index: 258

Text #18

Max Range: 5.5990. Min Range: -5.5990

Max Act: 3.1479. Min Act: -0.0000

Data Index: 510589 (C4 (Web Text))

Max Activating Token Index: 208

Text #19

Max Range: 5.5990. Min Range: -5.5990

Max Act: 3.1628. Min Act: -0.0000

Data Index: 1148283 (C4 (Web Text))

Max Activating Token Index: 973