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

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

Neuron 1406 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5029. Min Range: -0.5029

Max Act: 0.4977. Min Act: -0.0001

Data Index: 1631166 (Python Code)

Max Activating Token Index: 82

Text #1

Max Range: 0.5029. Min Range: -0.5029

Max Act: 0.4730. Min Act: -0.0001

Data Index: 1565985 (Python Code)

Max Activating Token Index: 622

Text #2

Max Range: 0.5029. Min Range: -0.5029

Max Act: 0.4936. Min Act: -0.0001

Data Index: 1540236 (Python Code)

Max Activating Token Index: 160

Text #3

Max Range: 0.5029. Min Range: -0.5029

Max Act: 0.4866. Min Act: -0.0001

Data Index: 1438656 (Python Code)

Max Activating Token Index: 101

Text #4

Max Range: 0.5029. Min Range: -0.5029

Max Act: 0.4830. Min Act: -0.0001

Data Index: 1546531 (Python Code)

Max Activating Token Index: 485

Text #5

Max Range: 0.5029. Min Range: -0.5029

Max Act: 0.4663. Min Act: -0.0001

Data Index: 1531287 (Python Code)

Max Activating Token Index: 455

Text #6

Max Range: 0.5029. Min Range: -0.5029

Max Act: 0.4817. Min Act: -0.0001

Data Index: 1594872 (Python Code)

Max Activating Token Index: 267

Text #7

Max Range: 0.5029. Min Range: -0.5029

Max Act: 0.4794. Min Act: -0.0001

Data Index: 1459904 (Python Code)

Max Activating Token Index: 398

Text #8

Max Range: 0.5029. Min Range: -0.5029

Max Act: 0.4802. Min Act: -0.0001

Data Index: 1476462 (Python Code)

Max Activating Token Index: 283

Text #9

Max Range: 0.5029. Min Range: -0.5029

Max Act: 0.4644. Min Act: -0.0001

Data Index: 1605749 (Python Code)

Max Activating Token Index: 504

Text #10

Max Range: 0.5029. Min Range: -0.5029

Max Act: 0.4500. Min Act: -0.0001

Data Index: 1390075 (Python Code)

Max Activating Token Index: 600

Text #11

Max Range: 0.5029. Min Range: -0.5029

Max Act: 0.4343. Min Act: -0.0001

Data Index: 1429678 (Python Code)

Max Activating Token Index: 55

Text #12

Max Range: 0.5029. Min Range: -0.5029

Max Act: 0.4226. Min Act: -0.0001

Data Index: 1525139 (Python Code)

Max Activating Token Index: 307

Text #13

Max Range: 0.5029. Min Range: -0.5029

Max Act: 0.4432. Min Act: -0.0001

Data Index: 1611760 (Python Code)

Max Activating Token Index: 180

Text #14

Max Range: 0.5029. Min Range: -0.5029

Max Act: 0.5029. Min Act: -0.0001

Data Index: 1642314 (Python Code)

Max Activating Token Index: 588

Text #15

Max Range: 0.5029. Min Range: -0.5029

Max Act: 0.4473. Min Act: -0.0001

Data Index: 1608303 (Python Code)

Max Activating Token Index: 501

Text #16

Max Range: 0.5029. Min Range: -0.5029

Max Act: 0.4593. Min Act: -0.0002

Data Index: 1576971 (Python Code)

Max Activating Token Index: 367

Text #17

Max Range: 0.5029. Min Range: -0.5029

Max Act: 0.4534. Min Act: -0.0001

Data Index: 1421936 (Python Code)

Max Activating Token Index: 127

Text #18

Max Range: 0.5029. Min Range: -0.5029

Max Act: 0.4488. Min Act: -0.0001

Data Index: 1480362 (Python Code)

Max Activating Token Index: 449

Text #19

Max Range: 0.5029. Min Range: -0.5029

Max Act: 0.4509. Min Act: -0.0001

Data Index: 1607750 (Python Code)

Max Activating Token Index: 255