Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2746 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.9545. Min Range: -0.9545

Max Act: 0.8967. Min Act: -0.0001

Data Index: 1624828 (Python Code)

Max Activating Token Index: 174

Text #1

Max Range: 0.9545. Min Range: -0.9545

Max Act: 0.9545. Min Act: -0.0001

Data Index: 1466235 (Python Code)

Max Activating Token Index: 442

Text #2

Max Range: 0.9545. Min Range: -0.9545

Max Act: 0.9248. Min Act: -0.0001

Data Index: 1423635 (Python Code)

Max Activating Token Index: 6

Text #3

Max Range: 0.9545. Min Range: -0.9545

Max Act: 0.9127. Min Act: -0.0001

Data Index: 1389289 (Python Code)

Max Activating Token Index: 983

Text #4

Max Range: 0.9545. Min Range: -0.9545

Max Act: 0.8851. Min Act: -0.0001

Data Index: 1589450 (Python Code)

Max Activating Token Index: 926

Text #5

Max Range: 0.9545. Min Range: -0.9545

Max Act: 0.9127. Min Act: -0.0001

Data Index: 1401323 (Python Code)

Max Activating Token Index: 321

Text #6

Max Range: 0.9545. Min Range: -0.9545

Max Act: 0.9028. Min Act: -0.0001

Data Index: 1643418 (Python Code)

Max Activating Token Index: 21

Text #7

Max Range: 0.9545. Min Range: -0.9545

Max Act: 0.8803. Min Act: -0.0001

Data Index: 1382362 (Python Code)

Max Activating Token Index: 10

Text #8

Max Range: 0.9545. Min Range: -0.9545

Max Act: 0.8444. Min Act: -0.0001

Data Index: 1473247 (Python Code)

Max Activating Token Index: 334

Text #9

Max Range: 0.9545. Min Range: -0.9545

Max Act: 0.8857. Min Act: -0.0001

Data Index: 1476706 (Python Code)

Max Activating Token Index: 22

Text #10

Max Range: 0.9545. Min Range: -0.9545

Max Act: 0.8566. Min Act: -0.0001

Data Index: 1559479 (Python Code)

Max Activating Token Index: 812

Text #11

Max Range: 0.9545. Min Range: -0.9545

Max Act: 0.8501. Min Act: -0.0001

Data Index: 1616818 (Python Code)

Max Activating Token Index: 233

Text #12

Max Range: 0.9545. Min Range: -0.9545

Max Act: 0.8189. Min Act: -0.0001

Data Index: 1643934 (Python Code)

Max Activating Token Index: 423

Text #13

Max Range: 0.9545. Min Range: -0.9545

Max Act: 0.8986. Min Act: -0.0001

Data Index: 1408355 (Python Code)

Max Activating Token Index: 788

Text #14

Max Range: 0.9545. Min Range: -0.9545

Max Act: 0.7870. Min Act: -0.0001

Data Index: 1550061 (Python Code)

Max Activating Token Index: 377

Text #15

Max Range: 0.9545. Min Range: -0.9545

Max Act: 0.8165. Min Act: -0.0001

Data Index: 1427097 (Python Code)

Max Activating Token Index: 52

Text #16

Max Range: 0.9545. Min Range: -0.9545

Max Act: 0.8420. Min Act: -0.0001

Data Index: 1463375 (Python Code)

Max Activating Token Index: 337

Text #17

Max Range: 0.9545. Min Range: -0.9545

Max Act: 0.8951. Min Act: -0.0001

Data Index: 1650819 (Python Code)

Max Activating Token Index: 601

Text #18

Max Range: 0.9545. Min Range: -0.9545

Max Act: 0.8368. Min Act: -0.0001

Data Index: 1648722 (Python Code)

Max Activating Token Index: 497

Text #19

Max Range: 0.9545. Min Range: -0.9545

Max Act: 0.8900. Min Act: -0.0001

Data Index: 1443499 (Python Code)

Max Activating Token Index: 363