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

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

Neuron 3502 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9273. Min Range: -0.9273

Max Act: 0.9273. Min Act: -0.0000

Data Index: 824901 (C4 (Web Text))

Max Activating Token Index: 497

Text #1

Max Range: 0.9273. Min Range: -0.9273

Max Act: 0.7491. Min Act: -0.0001

Data Index: 1335384 (C4 (Web Text))

Max Activating Token Index: 824

Text #2

Max Range: 0.9273. Min Range: -0.9273

Max Act: 0.8361. Min Act: -0.0000

Data Index: 259923 (C4 (Web Text))

Max Activating Token Index: 607

Text #3

Max Range: 0.9273. Min Range: -0.9273

Max Act: 0.8489. Min Act: -0.0000

Data Index: 1117616 (C4 (Web Text))

Max Activating Token Index: 682

Text #4

Max Range: 0.9273. Min Range: -0.9273

Max Act: 0.8082. Min Act: -0.0000

Data Index: 1004099 (C4 (Web Text))

Max Activating Token Index: 950

Text #5

Max Range: 0.9273. Min Range: -0.9273

Max Act: 0.7446. Min Act: -0.0000

Data Index: 1312335 (C4 (Web Text))

Max Activating Token Index: 809

Text #6

Max Range: 0.9273. Min Range: -0.9273

Max Act: 0.7768. Min Act: -0.0000

Data Index: 1110005 (C4 (Web Text))

Max Activating Token Index: 296

Text #7

Max Range: 0.9273. Min Range: -0.9273

Max Act: 0.7503. Min Act: -0.0000

Data Index: 230107 (C4 (Web Text))

Max Activating Token Index: 908

Text #8

Max Range: 0.9273. Min Range: -0.9273

Max Act: 0.7878. Min Act: -0.0001

Data Index: 836284 (C4 (Web Text))

Max Activating Token Index: 946

Text #9

Max Range: 0.9273. Min Range: -0.9273

Max Act: 0.7284. Min Act: -0.0000

Data Index: 297565 (C4 (Web Text))

Max Activating Token Index: 995

Text #10

Max Range: 0.9273. Min Range: -0.9273

Max Act: 0.7054. Min Act: -0.0000

Data Index: 933995 (C4 (Web Text))

Max Activating Token Index: 899

Text #11

Max Range: 0.9273. Min Range: -0.9273

Max Act: 0.7196. Min Act: -0.0000

Data Index: 503061 (C4 (Web Text))

Max Activating Token Index: 588

Text #12

Max Range: 0.9273. Min Range: -0.9273

Max Act: 0.6955. Min Act: -0.0000

Data Index: 252410 (C4 (Web Text))

Max Activating Token Index: 486

Text #13

Max Range: 0.9273. Min Range: -0.9273

Max Act: 0.6320. Min Act: -0.0000

Data Index: 751183 (C4 (Web Text))

Max Activating Token Index: 74

Text #14

Max Range: 0.9273. Min Range: -0.9273

Max Act: 0.6858. Min Act: -0.0000

Data Index: 406846 (C4 (Web Text))

Max Activating Token Index: 879

Text #15

Max Range: 0.9273. Min Range: -0.9273

Max Act: 0.7052. Min Act: -0.0000

Data Index: 207218 (C4 (Web Text))

Max Activating Token Index: 488

Text #16

Max Range: 0.9273. Min Range: -0.9273

Max Act: 0.6423. Min Act: -0.0000

Data Index: 1216969 (C4 (Web Text))

Max Activating Token Index: 653

Text #17

Max Range: 0.9273. Min Range: -0.9273

Max Act: 0.6533. Min Act: -0.0000

Data Index: 545209 (C4 (Web Text))

Max Activating Token Index: 782

Text #18

Max Range: 0.9273. Min Range: -0.9273

Max Act: 0.6821. Min Act: -0.0000

Data Index: 32531 (C4 (Web Text))

Max Activating Token Index: 257

Text #19

Max Range: 0.9273. Min Range: -0.9273

Max Act: 0.7149. Min Act: -0.0000

Data Index: 22208 (C4 (Web Text))

Max Activating Token Index: 459