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

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

Neuron 4012 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5439. Min Range: -1.5439

Max Act: 1.5439. Min Act: -0.0000

Data Index: 264660 (C4 (Web Text))

Max Activating Token Index: 619

Text #1

Max Range: 1.5439. Min Range: -1.5439

Max Act: 1.4367. Min Act: -0.0000

Data Index: 560199 (C4 (Web Text))

Max Activating Token Index: 496

Text #2

Max Range: 1.5439. Min Range: -1.5439

Max Act: 1.3190. Min Act: -0.0000

Data Index: 960964 (C4 (Web Text))

Max Activating Token Index: 196

Text #3

Max Range: 1.5439. Min Range: -1.5439

Max Act: 1.3327. Min Act: -0.0000

Data Index: 118287 (C4 (Web Text))

Max Activating Token Index: 453

Text #4

Max Range: 1.5439. Min Range: -1.5439

Max Act: 1.3123. Min Act: -0.0000

Data Index: 50384 (C4 (Web Text))

Max Activating Token Index: 998

Text #5

Max Range: 1.5439. Min Range: -1.5439

Max Act: 1.2920. Min Act: -0.0000

Data Index: 981850 (C4 (Web Text))

Max Activating Token Index: 441

Text #6

Max Range: 1.5439. Min Range: -1.5439

Max Act: 1.2951. Min Act: -0.0000

Data Index: 1001514 (C4 (Web Text))

Max Activating Token Index: 862

Text #7

Max Range: 1.5439. Min Range: -1.5439

Max Act: 1.1475. Min Act: -0.0000

Data Index: 749858 (C4 (Web Text))

Max Activating Token Index: 724

Text #8

Max Range: 1.5439. Min Range: -1.5439

Max Act: 1.1223. Min Act: -0.0000

Data Index: 983397 (C4 (Web Text))

Max Activating Token Index: 268

Text #9

Max Range: 1.5439. Min Range: -1.5439

Max Act: 1.0197. Min Act: -0.0000

Data Index: 1170872 (C4 (Web Text))

Max Activating Token Index: 740

Text #10

Max Range: 1.5439. Min Range: -1.5439

Max Act: 1.1127. Min Act: -0.0000

Data Index: 861799 (C4 (Web Text))

Max Activating Token Index: 72

Text #11

Max Range: 1.5439. Min Range: -1.5439

Max Act: 1.1099. Min Act: -0.0000

Data Index: 53211 (C4 (Web Text))

Max Activating Token Index: 29

Text #12

Max Range: 1.5439. Min Range: -1.5439

Max Act: 0.9487. Min Act: -0.0000

Data Index: 524491 (C4 (Web Text))

Max Activating Token Index: 571

Text #13

Max Range: 1.5439. Min Range: -1.5439

Max Act: 1.0952. Min Act: -0.0000

Data Index: 1127879 (C4 (Web Text))

Max Activating Token Index: 173

Text #14

Max Range: 1.5439. Min Range: -1.5439

Max Act: 1.0938. Min Act: -0.0000

Data Index: 727542 (C4 (Web Text))

Max Activating Token Index: 382

Text #15

Max Range: 1.5439. Min Range: -1.5439

Max Act: 1.0090. Min Act: -0.0000

Data Index: 1155017 (C4 (Web Text))

Max Activating Token Index: 892

Text #16

Max Range: 1.5439. Min Range: -1.5439

Max Act: 1.0716. Min Act: -0.0000

Data Index: 272686 (C4 (Web Text))

Max Activating Token Index: 274

Text #17

Max Range: 1.5439. Min Range: -1.5439

Max Act: 0.9843. Min Act: -0.0000

Data Index: 753847 (C4 (Web Text))

Max Activating Token Index: 327

Text #18

Max Range: 1.5439. Min Range: -1.5439

Max Act: 1.1048. Min Act: -0.0000

Data Index: 1056737 (C4 (Web Text))

Max Activating Token Index: 521

Text #19

Max Range: 1.5439. Min Range: -1.5439

Max Act: 1.0346. Min Act: -0.0000

Data Index: 846920 (C4 (Web Text))

Max Activating Token Index: 197