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

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

Neuron 3058 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7155. Min Range: -1.7155

Max Act: 1.7155. Min Act: -0.0000

Data Index: 1400292 (Python Code)

Max Activating Token Index: 909

Text #1

Max Range: 1.7155. Min Range: -1.7155

Max Act: 1.5702. Min Act: -0.0000

Data Index: 990575 (C4 (Web Text))

Max Activating Token Index: 543

Text #2

Max Range: 1.7155. Min Range: -1.7155

Max Act: 1.4699. Min Act: -0.0000

Data Index: 1497096 (Python Code)

Max Activating Token Index: 747

Text #3

Max Range: 1.7155. Min Range: -1.7155

Max Act: 1.4756. Min Act: -0.0000

Data Index: 218018 (C4 (Web Text))

Max Activating Token Index: 728

Text #4

Max Range: 1.7155. Min Range: -1.7155

Max Act: 1.4890. Min Act: -0.0000

Data Index: 122871 (C4 (Web Text))

Max Activating Token Index: 728

Text #5

Max Range: 1.7155. Min Range: -1.7155

Max Act: 1.3564. Min Act: -0.0000

Data Index: 1149959 (C4 (Web Text))

Max Activating Token Index: 907

Text #6

Max Range: 1.7155. Min Range: -1.7155

Max Act: 1.2718. Min Act: -0.0000

Data Index: 1586563 (Python Code)

Max Activating Token Index: 83

Text #7

Max Range: 1.7155. Min Range: -1.7155

Max Act: 1.2643. Min Act: -0.0000

Data Index: 532289 (C4 (Web Text))

Max Activating Token Index: 283

Text #8

Max Range: 1.7155. Min Range: -1.7155

Max Act: 1.2272. Min Act: -0.0000

Data Index: 441681 (C4 (Web Text))

Max Activating Token Index: 391

Text #9

Max Range: 1.7155. Min Range: -1.7155

Max Act: 1.2595. Min Act: -0.0000

Data Index: 1276858 (C4 (Web Text))

Max Activating Token Index: 271

Text #10

Max Range: 1.7155. Min Range: -1.7155

Max Act: 1.1336. Min Act: -0.0000

Data Index: 7059 (C4 (Web Text))

Max Activating Token Index: 612

Text #11

Max Range: 1.7155. Min Range: -1.7155

Max Act: 1.1960. Min Act: -0.0000

Data Index: 442498 (C4 (Web Text))

Max Activating Token Index: 1014

Text #12

Max Range: 1.7155. Min Range: -1.7155

Max Act: 1.1192. Min Act: -0.0000

Data Index: 1253054 (C4 (Web Text))

Max Activating Token Index: 1001

Text #13

Max Range: 1.7155. Min Range: -1.7155

Max Act: 1.1268. Min Act: -0.0000

Data Index: 596015 (C4 (Web Text))

Max Activating Token Index: 6

Text #14

Max Range: 1.7155. Min Range: -1.7155

Max Act: 1.0606. Min Act: -0.0000

Data Index: 953354 (C4 (Web Text))

Max Activating Token Index: 489

Text #15

Max Range: 1.7155. Min Range: -1.7155

Max Act: 1.0296. Min Act: -0.0000

Data Index: 1335904 (C4 (Web Text))

Max Activating Token Index: 421

Text #16

Max Range: 1.7155. Min Range: -1.7155

Max Act: 1.0098. Min Act: -0.0000

Data Index: 890585 (C4 (Web Text))

Max Activating Token Index: 370

Text #17

Max Range: 1.7155. Min Range: -1.7155

Max Act: 0.9981. Min Act: -0.0000

Data Index: 1147956 (C4 (Web Text))

Max Activating Token Index: 542

Text #18

Max Range: 1.7155. Min Range: -1.7155

Max Act: 0.9617. Min Act: -0.0000

Data Index: 1182448 (C4 (Web Text))

Max Activating Token Index: 237

Text #19

Max Range: 1.7155. Min Range: -1.7155

Max Act: 0.9927. Min Act: -0.0000

Data Index: 1089620 (C4 (Web Text))

Max Activating Token Index: 528