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

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

Neuron 3289 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: 1.9249. Min Range: -1.9249

Max Act: 1.9150. Min Act: -0.0001

Data Index: 1168453 (C4 (Web Text))

Max Activating Token Index: 692

Text #1

Max Range: 1.9249. Min Range: -1.9249

Max Act: 1.9249. Min Act: -0.0001

Data Index: 85258 (C4 (Web Text))

Max Activating Token Index: 5

Text #2

Max Range: 1.9249. Min Range: -1.9249

Max Act: 1.7908. Min Act: -0.0000

Data Index: 95421 (C4 (Web Text))

Max Activating Token Index: 42

Text #3

Max Range: 1.9249. Min Range: -1.9249

Max Act: 1.8553. Min Act: -0.0001

Data Index: 996362 (C4 (Web Text))

Max Activating Token Index: 641

Text #4

Max Range: 1.9249. Min Range: -1.9249

Max Act: 1.6323. Min Act: -0.0001

Data Index: 235161 (C4 (Web Text))

Max Activating Token Index: 741

Text #5

Max Range: 1.9249. Min Range: -1.9249

Max Act: 1.6878. Min Act: -0.0001

Data Index: 365500 (C4 (Web Text))

Max Activating Token Index: 647

Text #6

Max Range: 1.9249. Min Range: -1.9249

Max Act: 1.5865. Min Act: -0.0001

Data Index: 1086332 (C4 (Web Text))

Max Activating Token Index: 914

Text #7

Max Range: 1.9249. Min Range: -1.9249

Max Act: 1.6886. Min Act: -0.0001

Data Index: 658985 (C4 (Web Text))

Max Activating Token Index: 103

Text #8

Max Range: 1.9249. Min Range: -1.9249

Max Act: 1.5896. Min Act: -0.0001

Data Index: 165089 (C4 (Web Text))

Max Activating Token Index: 206

Text #9

Max Range: 1.9249. Min Range: -1.9249

Max Act: 1.5645. Min Act: -0.0001

Data Index: 639127 (C4 (Web Text))

Max Activating Token Index: 329

Text #10

Max Range: 1.9249. Min Range: -1.9249

Max Act: 1.6689. Min Act: -0.0001

Data Index: 1285195 (C4 (Web Text))

Max Activating Token Index: 569

Text #11

Max Range: 1.9249. Min Range: -1.9249

Max Act: 1.4591. Min Act: -0.0001

Data Index: 325016 (C4 (Web Text))

Max Activating Token Index: 281

Text #12

Max Range: 1.9249. Min Range: -1.9249

Max Act: 1.4706. Min Act: -0.0001

Data Index: 1156830 (C4 (Web Text))

Max Activating Token Index: 677

Text #13

Max Range: 1.9249. Min Range: -1.9249

Max Act: 1.4421. Min Act: -0.0001

Data Index: 778167 (C4 (Web Text))

Max Activating Token Index: 768

Text #14

Max Range: 1.9249. Min Range: -1.9249

Max Act: 1.5241. Min Act: -0.0001

Data Index: 1138915 (C4 (Web Text))

Max Activating Token Index: 33

Text #15

Max Range: 1.9249. Min Range: -1.9249

Max Act: 1.4454. Min Act: -0.0001

Data Index: 1248478 (C4 (Web Text))

Max Activating Token Index: 34

Text #16

Max Range: 1.9249. Min Range: -1.9249

Max Act: 1.4321. Min Act: -0.0001

Data Index: 1312502 (C4 (Web Text))

Max Activating Token Index: 43

Text #17

Max Range: 1.9249. Min Range: -1.9249

Max Act: 1.4349. Min Act: -0.0001

Data Index: 532962 (C4 (Web Text))

Max Activating Token Index: 660

Text #18

Max Range: 1.9249. Min Range: -1.9249

Max Act: 1.3293. Min Act: -0.0001

Data Index: 352892 (C4 (Web Text))

Max Activating Token Index: 122

Text #19

Max Range: 1.9249. Min Range: -1.9249

Max Act: 1.4781. Min Act: -0.0001

Data Index: 712282 (C4 (Web Text))

Max Activating Token Index: 885