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

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

Neuron 2375 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3630. Min Range: -3.3630

Max Act: 3.2451. Min Act: -0.0000

Data Index: 249103 (C4 (Web Text))

Max Activating Token Index: 236

Text #1

Max Range: 3.3630. Min Range: -3.3630

Max Act: 3.3630. Min Act: -0.0000

Data Index: 913122 (C4 (Web Text))

Max Activating Token Index: 463

Text #2

Max Range: 3.3630. Min Range: -3.3630

Max Act: 2.9293. Min Act: -0.0000

Data Index: 385195 (C4 (Web Text))

Max Activating Token Index: 407

Text #3

Max Range: 3.3630. Min Range: -3.3630

Max Act: 3.0967. Min Act: -0.0000

Data Index: 281912 (C4 (Web Text))

Max Activating Token Index: 444

Text #4

Max Range: 3.3630. Min Range: -3.3630

Max Act: 2.7038. Min Act: -0.0000

Data Index: 1113858 (C4 (Web Text))

Max Activating Token Index: 76

Text #5

Max Range: 3.3630. Min Range: -3.3630

Max Act: 2.7961. Min Act: -0.0000

Data Index: 385606 (C4 (Web Text))

Max Activating Token Index: 163

Text #6

Max Range: 3.3630. Min Range: -3.3630

Max Act: 2.9150. Min Act: -0.0000

Data Index: 369800 (C4 (Web Text))

Max Activating Token Index: 60

Text #7

Max Range: 3.3630. Min Range: -3.3630

Max Act: 2.8772. Min Act: -0.0000

Data Index: 1279545 (C4 (Web Text))

Max Activating Token Index: 687

Text #8

Max Range: 3.3630. Min Range: -3.3630

Max Act: 2.5767. Min Act: -0.0000

Data Index: 850350 (C4 (Web Text))

Max Activating Token Index: 476

Text #9

Max Range: 3.3630. Min Range: -3.3630

Max Act: 2.5530. Min Act: -0.0000

Data Index: 850776 (C4 (Web Text))

Max Activating Token Index: 202

Text #10

Max Range: 3.3630. Min Range: -3.3630

Max Act: 2.9420. Min Act: -0.0000

Data Index: 958233 (C4 (Web Text))

Max Activating Token Index: 959

Text #11

Max Range: 3.3630. Min Range: -3.3630

Max Act: 2.3838. Min Act: -0.0000

Data Index: 292362 (C4 (Web Text))

Max Activating Token Index: 115

Text #12

Max Range: 3.3630. Min Range: -3.3630

Max Act: 2.3892. Min Act: -0.0000

Data Index: 1131115 (C4 (Web Text))

Max Activating Token Index: 224

Text #13

Max Range: 3.3630. Min Range: -3.3630

Max Act: 2.4901. Min Act: -0.0000

Data Index: 1613092 (Python Code)

Max Activating Token Index: 249

Text #14

Max Range: 3.3630. Min Range: -3.3630

Max Act: 2.6113. Min Act: -0.0000

Data Index: 1469516 (Python Code)

Max Activating Token Index: 451

Text #15

Max Range: 3.3630. Min Range: -3.3630

Max Act: 2.3345. Min Act: -0.0000

Data Index: 1101745 (C4 (Web Text))

Max Activating Token Index: 63

Text #16

Max Range: 3.3630. Min Range: -3.3630

Max Act: 2.7308. Min Act: -0.0000

Data Index: 1095957 (C4 (Web Text))

Max Activating Token Index: 40

Text #17

Max Range: 3.3630. Min Range: -3.3630

Max Act: 2.8825. Min Act: -0.0000

Data Index: 1209131 (C4 (Web Text))

Max Activating Token Index: 740

Text #18

Max Range: 3.3630. Min Range: -3.3630

Max Act: 2.5923. Min Act: -0.0000

Data Index: 129245 (C4 (Web Text))

Max Activating Token Index: 835

Text #19

Max Range: 3.3630. Min Range: -3.3630

Max Act: 2.7096. Min Act: -0.0000

Data Index: 1299161 (C4 (Web Text))

Max Activating Token Index: 391