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

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

Neuron 30 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6329. Min Range: -0.6329

Max Act: 0.6329. Min Act: -0.0001

Data Index: 797761 (C4 (Web Text))

Max Activating Token Index: 533

Text #1

Max Range: 0.6329. Min Range: -0.6329

Max Act: 0.6166. Min Act: -0.0001

Data Index: 1235883 (C4 (Web Text))

Max Activating Token Index: 772

Text #2

Max Range: 0.6329. Min Range: -0.6329

Max Act: 0.6031. Min Act: -0.0001

Data Index: 468964 (C4 (Web Text))

Max Activating Token Index: 825

Text #3

Max Range: 0.6329. Min Range: -0.6329

Max Act: 0.6005. Min Act: -0.0001

Data Index: 485486 (C4 (Web Text))

Max Activating Token Index: 804

Text #4

Max Range: 0.6329. Min Range: -0.6329

Max Act: 0.5603. Min Act: -0.0001

Data Index: 549912 (C4 (Web Text))

Max Activating Token Index: 556

Text #5

Max Range: 0.6329. Min Range: -0.6329

Max Act: 0.5329. Min Act: -0.0001

Data Index: 25007 (C4 (Web Text))

Max Activating Token Index: 85

Text #6

Max Range: 0.6329. Min Range: -0.6329

Max Act: 0.5213. Min Act: -0.0001

Data Index: 1214482 (C4 (Web Text))

Max Activating Token Index: 262

Text #7

Max Range: 0.6329. Min Range: -0.6329

Max Act: 0.5295. Min Act: -0.0001

Data Index: 1249248 (C4 (Web Text))

Max Activating Token Index: 496

Text #8

Max Range: 0.6329. Min Range: -0.6329

Max Act: 0.5420. Min Act: -0.0001

Data Index: 293536 (C4 (Web Text))

Max Activating Token Index: 620

Text #9

Max Range: 0.6329. Min Range: -0.6329

Max Act: 0.5198. Min Act: -0.0001

Data Index: 600576 (C4 (Web Text))

Max Activating Token Index: 341

Text #10

Max Range: 0.6329. Min Range: -0.6329

Max Act: 0.5294. Min Act: -0.0001

Data Index: 1339597 (C4 (Web Text))

Max Activating Token Index: 705

Text #11

Max Range: 0.6329. Min Range: -0.6329

Max Act: 0.4984. Min Act: -0.0001

Data Index: 1111923 (C4 (Web Text))

Max Activating Token Index: 676

Text #12

Max Range: 0.6329. Min Range: -0.6329

Max Act: 0.4850. Min Act: -0.0001

Data Index: 353414 (C4 (Web Text))

Max Activating Token Index: 53

Text #13

Max Range: 0.6329. Min Range: -0.6329

Max Act: 0.5128. Min Act: -0.0001

Data Index: 933735 (C4 (Web Text))

Max Activating Token Index: 612

Text #14

Max Range: 0.6329. Min Range: -0.6329

Max Act: 0.5106. Min Act: -0.0001

Data Index: 1062138 (C4 (Web Text))

Max Activating Token Index: 392

Text #15

Max Range: 0.6329. Min Range: -0.6329

Max Act: 0.4820. Min Act: -0.0001

Data Index: 642270 (C4 (Web Text))

Max Activating Token Index: 292

Text #16

Max Range: 0.6329. Min Range: -0.6329

Max Act: 0.4689. Min Act: -0.0001

Data Index: 1080931 (C4 (Web Text))

Max Activating Token Index: 343

Text #17

Max Range: 0.6329. Min Range: -0.6329

Max Act: 0.4567. Min Act: -0.0001

Data Index: 812379 (C4 (Web Text))

Max Activating Token Index: 910

Text #18

Max Range: 0.6329. Min Range: -0.6329

Max Act: 0.4634. Min Act: -0.0001

Data Index: 1182807 (C4 (Web Text))

Max Activating Token Index: 208

Text #19

Max Range: 0.6329. Min Range: -0.6329

Max Act: 0.4520. Min Act: -0.0001

Data Index: 1145253 (C4 (Web Text))

Max Activating Token Index: 516