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

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

Neuron 197 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9855. Min Range: -0.9855

Max Act: 0.9855. Min Act: -0.0000

Data Index: 717870 (C4 (Web Text))

Max Activating Token Index: 455

Text #1

Max Range: 0.9855. Min Range: -0.9855

Max Act: 0.8438. Min Act: -0.0000

Data Index: 420113 (C4 (Web Text))

Max Activating Token Index: 318

Text #2

Max Range: 0.9855. Min Range: -0.9855

Max Act: 0.7353. Min Act: -0.0000

Data Index: 1144356 (C4 (Web Text))

Max Activating Token Index: 374

Text #3

Max Range: 0.9855. Min Range: -0.9855

Max Act: 0.6824. Min Act: -0.0000

Data Index: 525178 (C4 (Web Text))

Max Activating Token Index: 249

Text #4

Max Range: 0.9855. Min Range: -0.9855

Max Act: 0.6496. Min Act: -0.0000

Data Index: 751274 (C4 (Web Text))

Max Activating Token Index: 1000

Text #5

Max Range: 0.9855. Min Range: -0.9855

Max Act: 0.6298. Min Act: -0.0000

Data Index: 342977 (C4 (Web Text))

Max Activating Token Index: 916

Text #6

Max Range: 0.9855. Min Range: -0.9855

Max Act: 0.6465. Min Act: -0.0000

Data Index: 852717 (C4 (Web Text))

Max Activating Token Index: 196

Text #7

Max Range: 0.9855. Min Range: -0.9855

Max Act: 0.6855. Min Act: -0.0000

Data Index: 1450061 (Python Code)

Max Activating Token Index: 959

Text #8

Max Range: 0.9855. Min Range: -0.9855

Max Act: 0.5963. Min Act: -0.0000

Data Index: 187210 (C4 (Web Text))

Max Activating Token Index: 675

Text #9

Max Range: 0.9855. Min Range: -0.9855

Max Act: 0.6242. Min Act: -0.0000

Data Index: 699325 (C4 (Web Text))

Max Activating Token Index: 621

Text #10

Max Range: 0.9855. Min Range: -0.9855

Max Act: 0.5620. Min Act: -0.0000

Data Index: 1331704 (C4 (Web Text))

Max Activating Token Index: 269

Text #11

Max Range: 0.9855. Min Range: -0.9855

Max Act: 0.5962. Min Act: -0.0000

Data Index: 560201 (C4 (Web Text))

Max Activating Token Index: 427

Text #12

Max Range: 0.9855. Min Range: -0.9855

Max Act: 0.6084. Min Act: -0.0000

Data Index: 343182 (C4 (Web Text))

Max Activating Token Index: 99

Text #13

Max Range: 0.9855. Min Range: -0.9855

Max Act: 0.6259. Min Act: -0.0000

Data Index: 133897 (C4 (Web Text))

Max Activating Token Index: 737

Text #14

Max Range: 0.9855. Min Range: -0.9855

Max Act: 0.6210. Min Act: -0.0000

Data Index: 779486 (C4 (Web Text))

Max Activating Token Index: 296

Text #15

Max Range: 0.9855. Min Range: -0.9855

Max Act: 0.6043. Min Act: -0.0000

Data Index: 1113768 (C4 (Web Text))

Max Activating Token Index: 547

Text #16

Max Range: 0.9855. Min Range: -0.9855

Max Act: 0.6150. Min Act: -0.0000

Data Index: 1241308 (C4 (Web Text))

Max Activating Token Index: 925

Text #17

Max Range: 0.9855. Min Range: -0.9855

Max Act: 0.6120. Min Act: -0.0000

Data Index: 1339704 (C4 (Web Text))

Max Activating Token Index: 160

Text #18

Max Range: 0.9855. Min Range: -0.9855

Max Act: 0.6036. Min Act: -0.0000

Data Index: 1122640 (C4 (Web Text))

Max Activating Token Index: 22

Text #19

Max Range: 0.9855. Min Range: -0.9855

Max Act: 0.5827. Min Act: -0.0000

Data Index: 1623847 (Python Code)

Max Activating Token Index: 473