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

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

Neuron 3810 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9491. Min Range: -0.9491

Max Act: 0.9491. Min Act: -0.0001

Data Index: 1581958 (Python Code)

Max Activating Token Index: 691

Text #1

Max Range: 0.9491. Min Range: -0.9491

Max Act: 0.7307. Min Act: -0.0001

Data Index: 1463700 (Python Code)

Max Activating Token Index: 225

Text #2

Max Range: 0.9491. Min Range: -0.9491

Max Act: 0.7837. Min Act: -0.0001

Data Index: 1375004 (Python Code)

Max Activating Token Index: 100

Text #3

Max Range: 0.9491. Min Range: -0.9491

Max Act: 0.7405. Min Act: -0.0001

Data Index: 1412473 (Python Code)

Max Activating Token Index: 467

Text #4

Max Range: 0.9491. Min Range: -0.9491

Max Act: 0.7410. Min Act: -0.0001

Data Index: 1572575 (Python Code)

Max Activating Token Index: 260

Text #5

Max Range: 0.9491. Min Range: -0.9491

Max Act: 0.8352. Min Act: -0.0001

Data Index: 1401330 (Python Code)

Max Activating Token Index: 353

Text #6

Max Range: 0.9491. Min Range: -0.9491

Max Act: 0.6857. Min Act: -0.0001

Data Index: 1629812 (Python Code)

Max Activating Token Index: 441

Text #7

Max Range: 0.9491. Min Range: -0.9491

Max Act: 0.6961. Min Act: -0.0001

Data Index: 1489222 (Python Code)

Max Activating Token Index: 166

Text #8

Max Range: 0.9491. Min Range: -0.9491

Max Act: 0.7181. Min Act: -0.0001

Data Index: 1645073 (Python Code)

Max Activating Token Index: 467

Text #9

Max Range: 0.9491. Min Range: -0.9491

Max Act: 0.6877. Min Act: -0.0001

Data Index: 1428244 (Python Code)

Max Activating Token Index: 375

Text #10

Max Range: 0.9491. Min Range: -0.9491

Max Act: 0.6709. Min Act: -0.0001

Data Index: 1495262 (Python Code)

Max Activating Token Index: 14

Text #11

Max Range: 0.9491. Min Range: -0.9491

Max Act: 0.6955. Min Act: -0.0001

Data Index: 1539916 (Python Code)

Max Activating Token Index: 496

Text #12

Max Range: 0.9491. Min Range: -0.9491

Max Act: 0.7187. Min Act: -0.0001

Data Index: 1584531 (Python Code)

Max Activating Token Index: 200

Text #13

Max Range: 0.9491. Min Range: -0.9491

Max Act: 0.6901. Min Act: -0.0001

Data Index: 1500127 (Python Code)

Max Activating Token Index: 11

Text #14

Max Range: 0.9491. Min Range: -0.9491

Max Act: 0.6901. Min Act: -0.0001

Data Index: 1391878 (Python Code)

Max Activating Token Index: 11

Text #15

Max Range: 0.9491. Min Range: -0.9491

Max Act: 0.6901. Min Act: -0.0001

Data Index: 1460072 (Python Code)

Max Activating Token Index: 11

Text #16

Max Range: 0.9491. Min Range: -0.9491

Max Act: 0.7516. Min Act: -0.0001

Data Index: 1634161 (Python Code)

Max Activating Token Index: 41

Text #17

Max Range: 0.9491. Min Range: -0.9491

Max Act: 0.7231. Min Act: -0.0001

Data Index: 1371770 (Python Code)

Max Activating Token Index: 311

Text #18

Max Range: 0.9491. Min Range: -0.9491

Max Act: 0.7059. Min Act: -0.0001

Data Index: 1636737 (Python Code)

Max Activating Token Index: 15

Text #19

Max Range: 0.9491. Min Range: -0.9491

Max Act: 0.7173. Min Act: -0.0001

Data Index: 1516851 (Python Code)

Max Activating Token Index: 329