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

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

Neuron 3768 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.6231. Min Range: -0.6231

Max Act: 0.6231. Min Act: -0.0000

Data Index: 1291574 (C4 (Web Text))

Max Activating Token Index: 742

Text #1

Max Range: 0.6231. Min Range: -0.6231

Max Act: 0.5737. Min Act: -0.0000

Data Index: 1262057 (C4 (Web Text))

Max Activating Token Index: 583

Text #2

Max Range: 0.6231. Min Range: -0.6231

Max Act: 0.5326. Min Act: -0.0000

Data Index: 302779 (C4 (Web Text))

Max Activating Token Index: 213

Text #3

Max Range: 0.6231. Min Range: -0.6231

Max Act: 0.4881. Min Act: -0.0000

Data Index: 262594 (C4 (Web Text))

Max Activating Token Index: 714

Text #4

Max Range: 0.6231. Min Range: -0.6231

Max Act: 0.4279. Min Act: -0.0000

Data Index: 1338176 (C4 (Web Text))

Max Activating Token Index: 276

Text #5

Max Range: 0.6231. Min Range: -0.6231

Max Act: 0.3512. Min Act: -0.0000

Data Index: 1277671 (C4 (Web Text))

Max Activating Token Index: 759

Text #6

Max Range: 0.6231. Min Range: -0.6231

Max Act: 0.3435. Min Act: -0.0000

Data Index: 1028499 (C4 (Web Text))

Max Activating Token Index: 92

Text #7

Max Range: 0.6231. Min Range: -0.6231

Max Act: 0.3596. Min Act: -0.0000

Data Index: 21543 (C4 (Web Text))

Max Activating Token Index: 439

Text #8

Max Range: 0.6231. Min Range: -0.6231

Max Act: 0.3212. Min Act: -0.0000

Data Index: 308187 (C4 (Web Text))

Max Activating Token Index: 637

Text #9

Max Range: 0.6231. Min Range: -0.6231

Max Act: 0.3146. Min Act: -0.0000

Data Index: 104288 (C4 (Web Text))

Max Activating Token Index: 984

Text #10

Max Range: 0.6231. Min Range: -0.6231

Max Act: 0.3009. Min Act: -0.0000

Data Index: 1139640 (C4 (Web Text))

Max Activating Token Index: 735

Text #11

Max Range: 0.6231. Min Range: -0.6231

Max Act: 0.2699. Min Act: -0.0000

Data Index: 1333840 (C4 (Web Text))

Max Activating Token Index: 312

Text #12

Max Range: 0.6231. Min Range: -0.6231

Max Act: 0.2796. Min Act: -0.0000

Data Index: 1194508 (C4 (Web Text))

Max Activating Token Index: 800

Text #13

Max Range: 0.6231. Min Range: -0.6231

Max Act: 0.2784. Min Act: -0.0000

Data Index: 332019 (C4 (Web Text))

Max Activating Token Index: 712

Text #14

Max Range: 0.6231. Min Range: -0.6231

Max Act: 0.2930. Min Act: -0.0000

Data Index: 1104834 (C4 (Web Text))

Max Activating Token Index: 112

Text #15

Max Range: 0.6231. Min Range: -0.6231

Max Act: 0.2745. Min Act: -0.0000

Data Index: 106013 (C4 (Web Text))

Max Activating Token Index: 100

Text #16

Max Range: 0.6231. Min Range: -0.6231

Max Act: 0.2586. Min Act: -0.0000

Data Index: 673586 (C4 (Web Text))

Max Activating Token Index: 999

Text #17

Max Range: 0.6231. Min Range: -0.6231

Max Act: 0.2622. Min Act: -0.0000

Data Index: 1088547 (C4 (Web Text))

Max Activating Token Index: 840

Text #18

Max Range: 0.6231. Min Range: -0.6231

Max Act: 0.2591. Min Act: -0.0000

Data Index: 1425749 (Python Code)

Max Activating Token Index: 17

Text #19

Max Range: 0.6231. Min Range: -0.6231

Max Act: 0.2464. Min Act: -0.0000

Data Index: 1062626 (C4 (Web Text))

Max Activating Token Index: 553