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

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

Neuron 501 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: 2.5056. Min Range: -2.5056

Max Act: 2.5056. Min Act: -0.0000

Data Index: 1165363 (C4 (Web Text))

Max Activating Token Index: 162

Text #1

Max Range: 2.5056. Min Range: -2.5056

Max Act: 2.4406. Min Act: -0.0000

Data Index: 1203991 (C4 (Web Text))

Max Activating Token Index: 47

Text #2

Max Range: 2.5056. Min Range: -2.5056

Max Act: 2.3724. Min Act: -0.0000

Data Index: 141236 (C4 (Web Text))

Max Activating Token Index: 886

Text #3

Max Range: 2.5056. Min Range: -2.5056

Max Act: 2.0497. Min Act: -0.0000

Data Index: 1325675 (C4 (Web Text))

Max Activating Token Index: 691

Text #4

Max Range: 2.5056. Min Range: -2.5056

Max Act: 2.0418. Min Act: -0.0000

Data Index: 1057194 (C4 (Web Text))

Max Activating Token Index: 316

Text #5

Max Range: 2.5056. Min Range: -2.5056

Max Act: 2.0242. Min Act: -0.0000

Data Index: 525970 (C4 (Web Text))

Max Activating Token Index: 339

Text #6

Max Range: 2.5056. Min Range: -2.5056

Max Act: 2.0034. Min Act: -0.0000

Data Index: 757941 (C4 (Web Text))

Max Activating Token Index: 33

Text #7

Max Range: 2.5056. Min Range: -2.5056

Max Act: 1.9884. Min Act: -0.0000

Data Index: 901781 (C4 (Web Text))

Max Activating Token Index: 196

Text #8

Max Range: 2.5056. Min Range: -2.5056

Max Act: 1.8746. Min Act: -0.0000

Data Index: 661050 (C4 (Web Text))

Max Activating Token Index: 988

Text #9

Max Range: 2.5056. Min Range: -2.5056

Max Act: 1.9288. Min Act: -0.0000

Data Index: 216595 (C4 (Web Text))

Max Activating Token Index: 698

Text #10

Max Range: 2.5056. Min Range: -2.5056

Max Act: 1.8234. Min Act: -0.0000

Data Index: 773732 (C4 (Web Text))

Max Activating Token Index: 595

Text #11

Max Range: 2.5056. Min Range: -2.5056

Max Act: 1.7947. Min Act: -0.0000

Data Index: 305931 (C4 (Web Text))

Max Activating Token Index: 331

Text #12

Max Range: 2.5056. Min Range: -2.5056

Max Act: 1.9582. Min Act: -0.0000

Data Index: 1305992 (C4 (Web Text))

Max Activating Token Index: 197

Text #13

Max Range: 2.5056. Min Range: -2.5056

Max Act: 1.6727. Min Act: -0.0000

Data Index: 492557 (C4 (Web Text))

Max Activating Token Index: 774

Text #14

Max Range: 2.5056. Min Range: -2.5056

Max Act: 1.8533. Min Act: -0.0000

Data Index: 1232770 (C4 (Web Text))

Max Activating Token Index: 786

Text #15

Max Range: 2.5056. Min Range: -2.5056

Max Act: 1.7491. Min Act: -0.0000

Data Index: 325122 (C4 (Web Text))

Max Activating Token Index: 991

Text #16

Max Range: 2.5056. Min Range: -2.5056

Max Act: 1.7466. Min Act: -0.0000

Data Index: 749640 (C4 (Web Text))

Max Activating Token Index: 930

Text #17

Max Range: 2.5056. Min Range: -2.5056

Max Act: 1.7319. Min Act: -0.0000

Data Index: 1113906 (C4 (Web Text))

Max Activating Token Index: 228

Text #18

Max Range: 2.5056. Min Range: -2.5056

Max Act: 1.7523. Min Act: -0.0000

Data Index: 467879 (C4 (Web Text))

Max Activating Token Index: 874

Text #19

Max Range: 2.5056. Min Range: -2.5056

Max Act: 1.6478. Min Act: -0.0000

Data Index: 795643 (C4 (Web Text))

Max Activating Token Index: 175