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

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

Neuron 3350 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: 3.6443. Min Range: -3.6443

Max Act: 3.6443. Min Act: -0.0000

Data Index: 707843 (C4 (Web Text))

Max Activating Token Index: 882

Text #1

Max Range: 3.6443. Min Range: -3.6443

Max Act: 3.3872. Min Act: -0.0000

Data Index: 959685 (C4 (Web Text))

Max Activating Token Index: 989

Text #2

Max Range: 3.6443. Min Range: -3.6443

Max Act: 3.2197. Min Act: -0.0000

Data Index: 612209 (C4 (Web Text))

Max Activating Token Index: 616

Text #3

Max Range: 3.6443. Min Range: -3.6443

Max Act: 2.9176. Min Act: -0.0000

Data Index: 21457 (C4 (Web Text))

Max Activating Token Index: 304

Text #4

Max Range: 3.6443. Min Range: -3.6443

Max Act: 3.2011. Min Act: -0.0000

Data Index: 1061867 (C4 (Web Text))

Max Activating Token Index: 712

Text #5

Max Range: 3.6443. Min Range: -3.6443

Max Act: 3.1243. Min Act: -0.0000

Data Index: 1135643 (C4 (Web Text))

Max Activating Token Index: 110

Text #6

Max Range: 3.6443. Min Range: -3.6443

Max Act: 3.0836. Min Act: -0.0000

Data Index: 1316508 (C4 (Web Text))

Max Activating Token Index: 764

Text #7

Max Range: 3.6443. Min Range: -3.6443

Max Act: 3.3826. Min Act: -0.0000

Data Index: 753905 (C4 (Web Text))

Max Activating Token Index: 489

Text #8

Max Range: 3.6443. Min Range: -3.6443

Max Act: 3.0375. Min Act: -0.0000

Data Index: 927222 (C4 (Web Text))

Max Activating Token Index: 743

Text #9

Max Range: 3.6443. Min Range: -3.6443

Max Act: 3.0166. Min Act: -0.0000

Data Index: 62768 (C4 (Web Text))

Max Activating Token Index: 926

Text #10

Max Range: 3.6443. Min Range: -3.6443

Max Act: 2.9664. Min Act: -0.0000

Data Index: 881155 (C4 (Web Text))

Max Activating Token Index: 546

Text #11

Max Range: 3.6443. Min Range: -3.6443

Max Act: 3.1059. Min Act: -0.0000

Data Index: 834766 (C4 (Web Text))

Max Activating Token Index: 808

Text #12

Max Range: 3.6443. Min Range: -3.6443

Max Act: 2.9428. Min Act: -0.0000

Data Index: 1116287 (C4 (Web Text))

Max Activating Token Index: 747

Text #13

Max Range: 3.6443. Min Range: -3.6443

Max Act: 2.8042. Min Act: -0.0000

Data Index: 280082 (C4 (Web Text))

Max Activating Token Index: 498

Text #14

Max Range: 3.6443. Min Range: -3.6443

Max Act: 2.7874. Min Act: -0.0000

Data Index: 904305 (C4 (Web Text))

Max Activating Token Index: 625

Text #15

Max Range: 3.6443. Min Range: -3.6443

Max Act: 2.7966. Min Act: -0.0000

Data Index: 232242 (C4 (Web Text))

Max Activating Token Index: 216

Text #16

Max Range: 3.6443. Min Range: -3.6443

Max Act: 2.9425. Min Act: -0.0000

Data Index: 143016 (C4 (Web Text))

Max Activating Token Index: 281

Text #17

Max Range: 3.6443. Min Range: -3.6443

Max Act: 2.7880. Min Act: -0.0000

Data Index: 1000130 (C4 (Web Text))

Max Activating Token Index: 45

Text #18

Max Range: 3.6443. Min Range: -3.6443

Max Act: 2.8845. Min Act: -0.0000

Data Index: 829155 (C4 (Web Text))

Max Activating Token Index: 103

Text #19

Max Range: 3.6443. Min Range: -3.6443

Max Act: 3.0122. Min Act: -0.0000

Data Index: 1254747 (C4 (Web Text))

Max Activating Token Index: 633