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

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

Neuron 1338 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.0351. Min Range: -4.0351

Max Act: 3.9552. Min Act: -0.0000

Data Index: 1103466 (C4 (Web Text))

Max Activating Token Index: 380

Text #1

Max Range: 4.0351. Min Range: -4.0351

Max Act: 4.0351. Min Act: -0.0000

Data Index: 904654 (C4 (Web Text))

Max Activating Token Index: 561

Text #2

Max Range: 4.0351. Min Range: -4.0351

Max Act: 3.7880. Min Act: -0.0000

Data Index: 306409 (C4 (Web Text))

Max Activating Token Index: 556

Text #3

Max Range: 4.0351. Min Range: -4.0351

Max Act: 3.8936. Min Act: -0.0000

Data Index: 797617 (C4 (Web Text))

Max Activating Token Index: 415

Text #4

Max Range: 4.0351. Min Range: -4.0351

Max Act: 3.5420. Min Act: -0.0000

Data Index: 376050 (C4 (Web Text))

Max Activating Token Index: 682

Text #5

Max Range: 4.0351. Min Range: -4.0351

Max Act: 3.4984. Min Act: -0.0000

Data Index: 778864 (C4 (Web Text))

Max Activating Token Index: 147

Text #6

Max Range: 4.0351. Min Range: -4.0351

Max Act: 3.6405. Min Act: -0.0000

Data Index: 1046707 (C4 (Web Text))

Max Activating Token Index: 386

Text #7

Max Range: 4.0351. Min Range: -4.0351

Max Act: 3.5105. Min Act: -0.0000

Data Index: 939457 (C4 (Web Text))

Max Activating Token Index: 991

Text #8

Max Range: 4.0351. Min Range: -4.0351

Max Act: 3.2785. Min Act: -0.0000

Data Index: 1103569 (C4 (Web Text))

Max Activating Token Index: 219

Text #9

Max Range: 4.0351. Min Range: -4.0351

Max Act: 3.3745. Min Act: -0.0000

Data Index: 874798 (C4 (Web Text))

Max Activating Token Index: 526

Text #10

Max Range: 4.0351. Min Range: -4.0351

Max Act: 3.2664. Min Act: -0.0000

Data Index: 40542 (C4 (Web Text))

Max Activating Token Index: 17

Text #11

Max Range: 4.0351. Min Range: -4.0351

Max Act: 3.0975. Min Act: -0.0000

Data Index: 1278835 (C4 (Web Text))

Max Activating Token Index: 731

Text #12

Max Range: 4.0351. Min Range: -4.0351

Max Act: 3.0532. Min Act: -0.0000

Data Index: 912526 (C4 (Web Text))

Max Activating Token Index: 821

Text #13

Max Range: 4.0351. Min Range: -4.0351

Max Act: 3.3717. Min Act: -0.0000

Data Index: 1240935 (C4 (Web Text))

Max Activating Token Index: 654

Text #14

Max Range: 4.0351. Min Range: -4.0351

Max Act: 3.0155. Min Act: -0.0000

Data Index: 468802 (C4 (Web Text))

Max Activating Token Index: 800

Text #15

Max Range: 4.0351. Min Range: -4.0351

Max Act: 3.0061. Min Act: -0.0000

Data Index: 1278401 (C4 (Web Text))

Max Activating Token Index: 78

Text #16

Max Range: 4.0351. Min Range: -4.0351

Max Act: 3.1658. Min Act: -0.0000

Data Index: 1163823 (C4 (Web Text))

Max Activating Token Index: 262

Text #17

Max Range: 4.0351. Min Range: -4.0351

Max Act: 3.1531. Min Act: -0.0000

Data Index: 66740 (C4 (Web Text))

Max Activating Token Index: 231

Text #18

Max Range: 4.0351. Min Range: -4.0351

Max Act: 3.0728. Min Act: -0.0000

Data Index: 1186705 (C4 (Web Text))

Max Activating Token Index: 660

Text #19

Max Range: 4.0351. Min Range: -4.0351

Max Act: 2.9133. Min Act: -0.0000

Data Index: 223147 (C4 (Web Text))

Max Activating Token Index: 352