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

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

Neuron 574 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7099. Min Range: -0.7099

Max Act: 0.7099. Min Act: -0.0000

Data Index: 1393166 (Python Code)

Max Activating Token Index: 286

Text #1

Max Range: 0.7099. Min Range: -0.7099

Max Act: 0.6066. Min Act: -0.0000

Data Index: 1420260 (Python Code)

Max Activating Token Index: 461

Text #2

Max Range: 0.7099. Min Range: -0.7099

Max Act: 0.5729. Min Act: -0.0000

Data Index: 1432133 (Python Code)

Max Activating Token Index: 523

Text #3

Max Range: 0.7099. Min Range: -0.7099

Max Act: 0.5661. Min Act: -0.0000

Data Index: 1414549 (Python Code)

Max Activating Token Index: 331

Text #4

Max Range: 0.7099. Min Range: -0.7099

Max Act: 0.5316. Min Act: -0.0000

Data Index: 1365267 (Python Code)

Max Activating Token Index: 229

Text #5

Max Range: 0.7099. Min Range: -0.7099

Max Act: 0.5132. Min Act: -0.0000

Data Index: 1420032 (Python Code)

Max Activating Token Index: 894

Text #6

Max Range: 0.7099. Min Range: -0.7099

Max Act: 0.5132. Min Act: -0.0000

Data Index: 1431104 (Python Code)

Max Activating Token Index: 461

Text #7

Max Range: 0.7099. Min Range: -0.7099

Max Act: 0.5055. Min Act: -0.0000

Data Index: 1465650 (Python Code)

Max Activating Token Index: 158

Text #8

Max Range: 0.7099. Min Range: -0.7099

Max Act: 0.4177. Min Act: -0.0000

Data Index: 1449345 (Python Code)

Max Activating Token Index: 639

Text #9

Max Range: 0.7099. Min Range: -0.7099

Max Act: 0.4733. Min Act: -0.0000

Data Index: 1463081 (Python Code)

Max Activating Token Index: 172

Text #10

Max Range: 0.7099. Min Range: -0.7099

Max Act: 0.3791. Min Act: -0.0000

Data Index: 1418228 (Python Code)

Max Activating Token Index: 213

Text #11

Max Range: 0.7099. Min Range: -0.7099

Max Act: 0.4271. Min Act: -0.0000

Data Index: 1592647 (Python Code)

Max Activating Token Index: 773

Text #12

Max Range: 0.7099. Min Range: -0.7099

Max Act: 0.3950. Min Act: -0.0000

Data Index: 1478001 (Python Code)

Max Activating Token Index: 308

Text #13

Max Range: 0.7099. Min Range: -0.7099

Max Act: 0.4563. Min Act: -0.0000

Data Index: 1568718 (Python Code)

Max Activating Token Index: 273

Text #14

Max Range: 0.7099. Min Range: -0.7099

Max Act: 0.3968. Min Act: -0.0000

Data Index: 1389623 (Python Code)

Max Activating Token Index: 144

Text #15

Max Range: 0.7099. Min Range: -0.7099

Max Act: 0.4043. Min Act: -0.0000

Data Index: 1629327 (Python Code)

Max Activating Token Index: 241

Text #16

Max Range: 0.7099. Min Range: -0.7099

Max Act: 0.4147. Min Act: -0.0000

Data Index: 1412039 (Python Code)

Max Activating Token Index: 895

Text #17

Max Range: 0.7099. Min Range: -0.7099

Max Act: 0.3823. Min Act: -0.0000

Data Index: 1458356 (Python Code)

Max Activating Token Index: 218

Text #18

Max Range: 0.7099. Min Range: -0.7099

Max Act: 0.3940. Min Act: -0.0000

Data Index: 1515826 (Python Code)

Max Activating Token Index: 335

Text #19

Max Range: 0.7099. Min Range: -0.7099

Max Act: 0.3842. Min Act: -0.0000

Data Index: 1440689 (Python Code)

Max Activating Token Index: 63