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

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

Neuron 1388 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9066. Min Range: -0.9066

Max Act: 0.9066. Min Act: -0.0001

Data Index: 14609 (C4 (Web Text))

Max Activating Token Index: 421

Text #1

Max Range: 0.9066. Min Range: -0.9066

Max Act: 0.8138. Min Act: -0.0001

Data Index: 857257 (C4 (Web Text))

Max Activating Token Index: 940

Text #2

Max Range: 0.9066. Min Range: -0.9066

Max Act: 0.7511. Min Act: -0.0001

Data Index: 634186 (C4 (Web Text))

Max Activating Token Index: 833

Text #3

Max Range: 0.9066. Min Range: -0.9066

Max Act: 0.6912. Min Act: -0.0001

Data Index: 987330 (C4 (Web Text))

Max Activating Token Index: 594

Text #4

Max Range: 0.9066. Min Range: -0.9066

Max Act: 0.7212. Min Act: -0.0001

Data Index: 351319 (C4 (Web Text))

Max Activating Token Index: 867

Text #5

Max Range: 0.9066. Min Range: -0.9066

Max Act: 0.7333. Min Act: -0.0001

Data Index: 37062 (C4 (Web Text))

Max Activating Token Index: 650

Text #6

Max Range: 0.9066. Min Range: -0.9066

Max Act: 0.6931. Min Act: -0.0001

Data Index: 324245 (C4 (Web Text))

Max Activating Token Index: 621

Text #7

Max Range: 0.9066. Min Range: -0.9066

Max Act: 0.7336. Min Act: -0.0001

Data Index: 258131 (C4 (Web Text))

Max Activating Token Index: 424

Text #8

Max Range: 0.9066. Min Range: -0.9066

Max Act: 0.7030. Min Act: -0.0001

Data Index: 1276006 (C4 (Web Text))

Max Activating Token Index: 487

Text #9

Max Range: 0.9066. Min Range: -0.9066

Max Act: 0.6804. Min Act: -0.0001

Data Index: 1306123 (C4 (Web Text))

Max Activating Token Index: 579

Text #10

Max Range: 0.9066. Min Range: -0.9066

Max Act: 0.7128. Min Act: -0.0001

Data Index: 462056 (C4 (Web Text))

Max Activating Token Index: 993

Text #11

Max Range: 0.9066. Min Range: -0.9066

Max Act: 0.6099. Min Act: -0.0001

Data Index: 650053 (C4 (Web Text))

Max Activating Token Index: 654

Text #12

Max Range: 0.9066. Min Range: -0.9066

Max Act: 0.6396. Min Act: -0.0001

Data Index: 1152245 (C4 (Web Text))

Max Activating Token Index: 60

Text #13

Max Range: 0.9066. Min Range: -0.9066

Max Act: 0.6724. Min Act: -0.0001

Data Index: 404295 (C4 (Web Text))

Max Activating Token Index: 851

Text #14

Max Range: 0.9066. Min Range: -0.9066

Max Act: 0.6405. Min Act: -0.0001

Data Index: 580857 (C4 (Web Text))

Max Activating Token Index: 811

Text #15

Max Range: 0.9066. Min Range: -0.9066

Max Act: 0.6866. Min Act: -0.0001

Data Index: 129437 (C4 (Web Text))

Max Activating Token Index: 162

Text #16

Max Range: 0.9066. Min Range: -0.9066

Max Act: 0.6595. Min Act: -0.0001

Data Index: 471742 (C4 (Web Text))

Max Activating Token Index: 159

Text #17

Max Range: 0.9066. Min Range: -0.9066

Max Act: 0.5994. Min Act: -0.0001

Data Index: 1139096 (C4 (Web Text))

Max Activating Token Index: 299

Text #18

Max Range: 0.9066. Min Range: -0.9066

Max Act: 0.6535. Min Act: -0.0001

Data Index: 309152 (C4 (Web Text))

Max Activating Token Index: 642

Text #19

Max Range: 0.9066. Min Range: -0.9066

Max Act: 0.6386. Min Act: -0.0001

Data Index: 249783 (C4 (Web Text))

Max Activating Token Index: 16