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

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

Neuron 5750 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0412. Min Range: -1.0412

Max Act: 1.0412. Min Act: -0.0000

Data Index: 570805 (C4 (Web Text))

Max Activating Token Index: 518

Text #1

Max Range: 1.0412. Min Range: -1.0412

Max Act: 0.9012. Min Act: -0.0000

Data Index: 1067245 (C4 (Web Text))

Max Activating Token Index: 181

Text #2

Max Range: 1.0412. Min Range: -1.0412

Max Act: 0.9441. Min Act: -0.0000

Data Index: 482143 (C4 (Web Text))

Max Activating Token Index: 400

Text #3

Max Range: 1.0412. Min Range: -1.0412

Max Act: 0.9452. Min Act: -0.0000

Data Index: 780040 (C4 (Web Text))

Max Activating Token Index: 404

Text #4

Max Range: 1.0412. Min Range: -1.0412

Max Act: 0.8665. Min Act: 0.0000

Data Index: 309129 (C4 (Web Text))

Max Activating Token Index: 471

Text #5

Max Range: 1.0412. Min Range: -1.0412

Max Act: 0.7757. Min Act: -0.0000

Data Index: 35066 (C4 (Web Text))

Max Activating Token Index: 1011

Text #6

Max Range: 1.0412. Min Range: -1.0412

Max Act: 0.7536. Min Act: 0.0000

Data Index: 1210394 (C4 (Web Text))

Max Activating Token Index: 375

Text #7

Max Range: 1.0412. Min Range: -1.0412

Max Act: 0.7737. Min Act: -0.0000

Data Index: 806356 (C4 (Web Text))

Max Activating Token Index: 942

Text #8

Max Range: 1.0412. Min Range: -1.0412

Max Act: 0.7591. Min Act: -0.0000

Data Index: 748171 (C4 (Web Text))

Max Activating Token Index: 500

Text #9

Max Range: 1.0412. Min Range: -1.0412

Max Act: 0.7754. Min Act: 0.0000

Data Index: 490949 (C4 (Web Text))

Max Activating Token Index: 727

Text #10

Max Range: 1.0412. Min Range: -1.0412

Max Act: 0.7905. Min Act: -0.0000

Data Index: 1215255 (C4 (Web Text))

Max Activating Token Index: 857

Text #11

Max Range: 1.0412. Min Range: -1.0412

Max Act: 0.7402. Min Act: -0.0000

Data Index: 267686 (C4 (Web Text))

Max Activating Token Index: 325

Text #12

Max Range: 1.0412. Min Range: -1.0412

Max Act: 0.7297. Min Act: -0.0000

Data Index: 955248 (C4 (Web Text))

Max Activating Token Index: 171

Text #13

Max Range: 1.0412. Min Range: -1.0412

Max Act: 0.7012. Min Act: -0.0000

Data Index: 3407 (C4 (Web Text))

Max Activating Token Index: 430

Text #14

Max Range: 1.0412. Min Range: -1.0412

Max Act: 0.7632. Min Act: -0.0000

Data Index: 40839 (C4 (Web Text))

Max Activating Token Index: 919

Text #15

Max Range: 1.0412. Min Range: -1.0412

Max Act: 0.7177. Min Act: -0.0000

Data Index: 837097 (C4 (Web Text))

Max Activating Token Index: 352

Text #16

Max Range: 1.0412. Min Range: -1.0412

Max Act: 0.7124. Min Act: -0.0000

Data Index: 173035 (C4 (Web Text))

Max Activating Token Index: 563

Text #17

Max Range: 1.0412. Min Range: -1.0412

Max Act: 0.7129. Min Act: -0.0000

Data Index: 386175 (C4 (Web Text))

Max Activating Token Index: 161

Text #18

Max Range: 1.0412. Min Range: -1.0412

Max Act: 0.7610. Min Act: -0.0000

Data Index: 970652 (C4 (Web Text))

Max Activating Token Index: 233

Text #19

Max Range: 1.0412. Min Range: -1.0412

Max Act: 0.7079. Min Act: -0.0000

Data Index: 647258 (C4 (Web Text))

Max Activating Token Index: 388