Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2199 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.2973. Min Range: -1.2973

Max Act: 1.2973. Min Act: -0.0001

Data Index: 400050 (C4 (Web Text))

Max Activating Token Index: 879

Text #1

Max Range: 1.2973. Min Range: -1.2973

Max Act: 1.2093. Min Act: -0.0001

Data Index: 603845 (C4 (Web Text))

Max Activating Token Index: 876

Text #2

Max Range: 1.2973. Min Range: -1.2973

Max Act: 1.2686. Min Act: -0.0001

Data Index: 475952 (C4 (Web Text))

Max Activating Token Index: 755

Text #3

Max Range: 1.2973. Min Range: -1.2973

Max Act: 1.0916. Min Act: -0.0001

Data Index: 81826 (C4 (Web Text))

Max Activating Token Index: 400

Text #4

Max Range: 1.2973. Min Range: -1.2973

Max Act: 0.9438. Min Act: -0.0001

Data Index: 798659 (C4 (Web Text))

Max Activating Token Index: 281

Text #5

Max Range: 1.2973. Min Range: -1.2973

Max Act: 0.9931. Min Act: -0.0001

Data Index: 1282799 (C4 (Web Text))

Max Activating Token Index: 858

Text #6

Max Range: 1.2973. Min Range: -1.2973

Max Act: 1.0029. Min Act: -0.0001

Data Index: 862997 (C4 (Web Text))

Max Activating Token Index: 905

Text #7

Max Range: 1.2973. Min Range: -1.2973

Max Act: 1.0143. Min Act: -0.0001

Data Index: 1315492 (C4 (Web Text))

Max Activating Token Index: 642

Text #8

Max Range: 1.2973. Min Range: -1.2973

Max Act: 0.9843. Min Act: -0.0001

Data Index: 1231103 (C4 (Web Text))

Max Activating Token Index: 810

Text #9

Max Range: 1.2973. Min Range: -1.2973

Max Act: 0.8961. Min Act: -0.0001

Data Index: 939135 (C4 (Web Text))

Max Activating Token Index: 891

Text #10

Max Range: 1.2973. Min Range: -1.2973

Max Act: 0.8166. Min Act: -0.0001

Data Index: 1209358 (C4 (Web Text))

Max Activating Token Index: 625

Text #11

Max Range: 1.2973. Min Range: -1.2973

Max Act: 0.7377. Min Act: -0.0001

Data Index: 668382 (C4 (Web Text))

Max Activating Token Index: 676

Text #12

Max Range: 1.2973. Min Range: -1.2973

Max Act: 0.7252. Min Act: -0.0001

Data Index: 124130 (C4 (Web Text))

Max Activating Token Index: 719

Text #13

Max Range: 1.2973. Min Range: -1.2973

Max Act: 0.7348. Min Act: -0.0001

Data Index: 1068694 (C4 (Web Text))

Max Activating Token Index: 323

Text #14

Max Range: 1.2973. Min Range: -1.2973

Max Act: 0.7481. Min Act: -0.0001

Data Index: 812734 (C4 (Web Text))

Max Activating Token Index: 557

Text #15

Max Range: 1.2973. Min Range: -1.2973

Max Act: 0.6850. Min Act: -0.0001

Data Index: 1215624 (C4 (Web Text))

Max Activating Token Index: 763

Text #16

Max Range: 1.2973. Min Range: -1.2973

Max Act: 0.6969. Min Act: -0.0001

Data Index: 798794 (C4 (Web Text))

Max Activating Token Index: 703

Text #17

Max Range: 1.2973. Min Range: -1.2973

Max Act: 0.6628. Min Act: -0.0001

Data Index: 417006 (C4 (Web Text))

Max Activating Token Index: 250

Text #18

Max Range: 1.2973. Min Range: -1.2973

Max Act: 0.5996. Min Act: -0.0001

Data Index: 628868 (C4 (Web Text))

Max Activating Token Index: 636

Text #19

Max Range: 1.2973. Min Range: -1.2973

Max Act: 0.6539. Min Act: -0.0001

Data Index: 743398 (C4 (Web Text))

Max Activating Token Index: 225