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

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

Neuron 4423 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: 1.3422. Min Range: -1.3422

Max Act: 1.3422. Min Act: -0.0000

Data Index: 375272 (C4 (Web Text))

Max Activating Token Index: 896

Text #1

Max Range: 1.3422. Min Range: -1.3422

Max Act: 1.2331. Min Act: -0.0000

Data Index: 329956 (C4 (Web Text))

Max Activating Token Index: 560

Text #2

Max Range: 1.3422. Min Range: -1.3422

Max Act: 1.2374. Min Act: -0.0000

Data Index: 114536 (C4 (Web Text))

Max Activating Token Index: 736

Text #3

Max Range: 1.3422. Min Range: -1.3422

Max Act: 1.1638. Min Act: -0.0000

Data Index: 286165 (C4 (Web Text))

Max Activating Token Index: 859

Text #4

Max Range: 1.3422. Min Range: -1.3422

Max Act: 1.1159. Min Act: -0.0000

Data Index: 823120 (C4 (Web Text))

Max Activating Token Index: 309

Text #5

Max Range: 1.3422. Min Range: -1.3422

Max Act: 1.2013. Min Act: -0.0000

Data Index: 540542 (C4 (Web Text))

Max Activating Token Index: 397

Text #6

Max Range: 1.3422. Min Range: -1.3422

Max Act: 1.1679. Min Act: -0.0000

Data Index: 274511 (C4 (Web Text))

Max Activating Token Index: 820

Text #7

Max Range: 1.3422. Min Range: -1.3422

Max Act: 1.0519. Min Act: -0.0000

Data Index: 156698 (C4 (Web Text))

Max Activating Token Index: 215

Text #8

Max Range: 1.3422. Min Range: -1.3422

Max Act: 1.0133. Min Act: -0.0000

Data Index: 940872 (C4 (Web Text))

Max Activating Token Index: 699

Text #9

Max Range: 1.3422. Min Range: -1.3422

Max Act: 1.0656. Min Act: -0.0000

Data Index: 736607 (C4 (Web Text))

Max Activating Token Index: 333

Text #10

Max Range: 1.3422. Min Range: -1.3422

Max Act: 1.0275. Min Act: -0.0000

Data Index: 1073172 (C4 (Web Text))

Max Activating Token Index: 971

Text #11

Max Range: 1.3422. Min Range: -1.3422

Max Act: 1.0977. Min Act: -0.0000

Data Index: 598720 (C4 (Web Text))

Max Activating Token Index: 687

Text #12

Max Range: 1.3422. Min Range: -1.3422

Max Act: 0.9966. Min Act: -0.0000

Data Index: 1172832 (C4 (Web Text))

Max Activating Token Index: 295

Text #13

Max Range: 1.3422. Min Range: -1.3422

Max Act: 1.0815. Min Act: -0.0000

Data Index: 532709 (C4 (Web Text))

Max Activating Token Index: 959

Text #14

Max Range: 1.3422. Min Range: -1.3422

Max Act: 0.9584. Min Act: -0.0000

Data Index: 1257771 (C4 (Web Text))

Max Activating Token Index: 735

Text #15

Max Range: 1.3422. Min Range: -1.3422

Max Act: 1.0406. Min Act: -0.0000

Data Index: 596536 (C4 (Web Text))

Max Activating Token Index: 442

Text #16

Max Range: 1.3422. Min Range: -1.3422

Max Act: 1.0038. Min Act: -0.0000

Data Index: 986316 (C4 (Web Text))

Max Activating Token Index: 167

Text #17

Max Range: 1.3422. Min Range: -1.3422

Max Act: 1.0439. Min Act: -0.0001

Data Index: 766643 (C4 (Web Text))

Max Activating Token Index: 295

Text #18

Max Range: 1.3422. Min Range: -1.3422

Max Act: 0.9983. Min Act: -0.0000

Data Index: 1100135 (C4 (Web Text))

Max Activating Token Index: 236

Text #19

Max Range: 1.3422. Min Range: -1.3422

Max Act: 0.8814. Min Act: -0.0000

Data Index: 23064 (C4 (Web Text))

Max Activating Token Index: 257