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

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

Neuron 2379 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 5.7956. Min Range: -5.7956

Max Act: 5.7956. Min Act: -0.0000

Data Index: 68897 (C4 (Web Text))

Max Activating Token Index: 107

Text #1

Max Range: 5.7956. Min Range: -5.7956

Max Act: 5.5009. Min Act: -0.0000

Data Index: 927316 (C4 (Web Text))

Max Activating Token Index: 978

Text #2

Max Range: 5.7956. Min Range: -5.7956

Max Act: 4.1355. Min Act: -0.0000

Data Index: 746711 (C4 (Web Text))

Max Activating Token Index: 594

Text #3

Max Range: 5.7956. Min Range: -5.7956

Max Act: 5.0440. Min Act: -0.0000

Data Index: 381394 (C4 (Web Text))

Max Activating Token Index: 1007

Text #4

Max Range: 5.7956. Min Range: -5.7956

Max Act: 4.8589. Min Act: -0.0000

Data Index: 934827 (C4 (Web Text))

Max Activating Token Index: 460

Text #5

Max Range: 5.7956. Min Range: -5.7956

Max Act: 4.6125. Min Act: -0.0000

Data Index: 547986 (C4 (Web Text))

Max Activating Token Index: 551

Text #6

Max Range: 5.7956. Min Range: -5.7956

Max Act: 4.2383. Min Act: -0.0000

Data Index: 106470 (C4 (Web Text))

Max Activating Token Index: 257

Text #7

Max Range: 5.7956. Min Range: -5.7956

Max Act: 4.5962. Min Act: -0.0000

Data Index: 946597 (C4 (Web Text))

Max Activating Token Index: 238

Text #8

Max Range: 5.7956. Min Range: -5.7956

Max Act: 4.5901. Min Act: -0.0000

Data Index: 1288850 (C4 (Web Text))

Max Activating Token Index: 749

Text #9

Max Range: 5.7956. Min Range: -5.7956

Max Act: 4.3590. Min Act: -0.0000

Data Index: 107043 (C4 (Web Text))

Max Activating Token Index: 710

Text #10

Max Range: 5.7956. Min Range: -5.7956

Max Act: 4.4870. Min Act: -0.0000

Data Index: 1250147 (C4 (Web Text))

Max Activating Token Index: 551

Text #11

Max Range: 5.7956. Min Range: -5.7956

Max Act: 4.2927. Min Act: -0.0001

Data Index: 758849 (C4 (Web Text))

Max Activating Token Index: 832

Text #12

Max Range: 5.7956. Min Range: -5.7956

Max Act: 3.8913. Min Act: -0.0000

Data Index: 246308 (C4 (Web Text))

Max Activating Token Index: 283

Text #13

Max Range: 5.7956. Min Range: -5.7956

Max Act: 4.0520. Min Act: -0.0000

Data Index: 180963 (C4 (Web Text))

Max Activating Token Index: 644

Text #14

Max Range: 5.7956. Min Range: -5.7956

Max Act: 4.2946. Min Act: -0.0000

Data Index: 60300 (C4 (Web Text))

Max Activating Token Index: 625

Text #15

Max Range: 5.7956. Min Range: -5.7956

Max Act: 4.6045. Min Act: -0.0000

Data Index: 1212695 (C4 (Web Text))

Max Activating Token Index: 839

Text #16

Max Range: 5.7956. Min Range: -5.7956

Max Act: 4.6226. Min Act: -0.0000

Data Index: 877889 (C4 (Web Text))

Max Activating Token Index: 599

Text #17

Max Range: 5.7956. Min Range: -5.7956

Max Act: 4.4423. Min Act: -0.0000

Data Index: 868532 (C4 (Web Text))

Max Activating Token Index: 444

Text #18

Max Range: 5.7956. Min Range: -5.7956

Max Act: 4.1113. Min Act: -0.0000

Data Index: 84035 (C4 (Web Text))

Max Activating Token Index: 984

Text #19

Max Range: 5.7956. Min Range: -5.7956

Max Act: 4.2026. Min Act: -0.0000

Data Index: 1186120 (C4 (Web Text))

Max Activating Token Index: 874