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

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

Neuron 726 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9388. Min Range: -0.9388

Max Act: 0.9388. Min Act: -0.0000

Data Index: 769145 (C4 (Web Text))

Max Activating Token Index: 371

Text #1

Max Range: 0.9388. Min Range: -0.9388

Max Act: 0.8597. Min Act: -0.0000

Data Index: 53108 (C4 (Web Text))

Max Activating Token Index: 877

Text #2

Max Range: 0.9388. Min Range: -0.9388

Max Act: 0.7767. Min Act: -0.0000

Data Index: 893442 (C4 (Web Text))

Max Activating Token Index: 312

Text #3

Max Range: 0.9388. Min Range: -0.9388

Max Act: 0.7158. Min Act: -0.0000

Data Index: 504137 (C4 (Web Text))

Max Activating Token Index: 510

Text #4

Max Range: 0.9388. Min Range: -0.9388

Max Act: 0.6673. Min Act: -0.0000

Data Index: 592161 (C4 (Web Text))

Max Activating Token Index: 223

Text #5

Max Range: 0.9388. Min Range: -0.9388

Max Act: 0.6462. Min Act: -0.0000

Data Index: 609249 (C4 (Web Text))

Max Activating Token Index: 250

Text #6

Max Range: 0.9388. Min Range: -0.9388

Max Act: 0.6860. Min Act: -0.0000

Data Index: 1241001 (C4 (Web Text))

Max Activating Token Index: 511

Text #7

Max Range: 0.9388. Min Range: -0.9388

Max Act: 0.6383. Min Act: -0.0000

Data Index: 873045 (C4 (Web Text))

Max Activating Token Index: 885

Text #8

Max Range: 0.9388. Min Range: -0.9388

Max Act: 0.5545. Min Act: -0.0000

Data Index: 27022 (C4 (Web Text))

Max Activating Token Index: 902

Text #9

Max Range: 0.9388. Min Range: -0.9388

Max Act: 0.6371. Min Act: -0.0000

Data Index: 648704 (C4 (Web Text))

Max Activating Token Index: 431

Text #10

Max Range: 0.9388. Min Range: -0.9388

Max Act: 0.7323. Min Act: -0.0000

Data Index: 324312 (C4 (Web Text))

Max Activating Token Index: 231

Text #11

Max Range: 0.9388. Min Range: -0.9388

Max Act: 0.5776. Min Act: -0.0000

Data Index: 71127 (C4 (Web Text))

Max Activating Token Index: 459

Text #12

Max Range: 0.9388. Min Range: -0.9388

Max Act: 0.6477. Min Act: -0.0000

Data Index: 1085573 (C4 (Web Text))

Max Activating Token Index: 860

Text #13

Max Range: 0.9388. Min Range: -0.9388

Max Act: 0.5760. Min Act: -0.0000

Data Index: 718352 (C4 (Web Text))

Max Activating Token Index: 179

Text #14

Max Range: 0.9388. Min Range: -0.9388

Max Act: 0.5916. Min Act: -0.0000

Data Index: 825253 (C4 (Web Text))

Max Activating Token Index: 681

Text #15

Max Range: 0.9388. Min Range: -0.9388

Max Act: 0.6578. Min Act: -0.0000

Data Index: 1116556 (C4 (Web Text))

Max Activating Token Index: 170

Text #16

Max Range: 0.9388. Min Range: -0.9388

Max Act: 0.5497. Min Act: -0.0000

Data Index: 1151252 (C4 (Web Text))

Max Activating Token Index: 356

Text #17

Max Range: 0.9388. Min Range: -0.9388

Max Act: 0.5633. Min Act: -0.0000

Data Index: 587246 (C4 (Web Text))

Max Activating Token Index: 237

Text #18

Max Range: 0.9388. Min Range: -0.9388

Max Act: 0.5747. Min Act: -0.0000

Data Index: 1163617 (C4 (Web Text))

Max Activating Token Index: 288

Text #19

Max Range: 0.9388. Min Range: -0.9388

Max Act: 0.5814. Min Act: -0.0000

Data Index: 716508 (C4 (Web Text))

Max Activating Token Index: 839