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

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

Neuron 3414 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6100. Min Range: -0.6100

Max Act: 0.6100. Min Act: -0.0000

Data Index: 334470 (C4 (Web Text))

Max Activating Token Index: 873

Text #1

Max Range: 0.6100. Min Range: -0.6100

Max Act: 0.6059. Min Act: -0.0001

Data Index: 1408880 (Python Code)

Max Activating Token Index: 103

Text #2

Max Range: 0.6100. Min Range: -0.6100

Max Act: 0.5392. Min Act: -0.0001

Data Index: 1471763 (Python Code)

Max Activating Token Index: 1002

Text #3

Max Range: 0.6100. Min Range: -0.6100

Max Act: 0.5441. Min Act: -0.0001

Data Index: 1529447 (Python Code)

Max Activating Token Index: 622

Text #4

Max Range: 0.6100. Min Range: -0.6100

Max Act: 0.5427. Min Act: -0.0001

Data Index: 1555898 (Python Code)

Max Activating Token Index: 632

Text #5

Max Range: 0.6100. Min Range: -0.6100

Max Act: 0.5115. Min Act: -0.0001

Data Index: 1551521 (Python Code)

Max Activating Token Index: 474

Text #6

Max Range: 0.6100. Min Range: -0.6100

Max Act: 0.5245. Min Act: -0.0001

Data Index: 1606351 (Python Code)

Max Activating Token Index: 417

Text #7

Max Range: 0.6100. Min Range: -0.6100

Max Act: 0.5380. Min Act: -0.0001

Data Index: 1553440 (Python Code)

Max Activating Token Index: 80

Text #8

Max Range: 0.6100. Min Range: -0.6100

Max Act: 0.5172. Min Act: -0.0001

Data Index: 1656300 (Python Code)

Max Activating Token Index: 299

Text #9

Max Range: 0.6100. Min Range: -0.6100

Max Act: 0.4937. Min Act: -0.0001

Data Index: 1395756 (Python Code)

Max Activating Token Index: 538

Text #10

Max Range: 0.6100. Min Range: -0.6100

Max Act: 0.4924. Min Act: -0.0000

Data Index: 1647042 (Python Code)

Max Activating Token Index: 306

Text #11

Max Range: 0.6100. Min Range: -0.6100

Max Act: 0.4850. Min Act: -0.0001

Data Index: 1488548 (Python Code)

Max Activating Token Index: 788

Text #12

Max Range: 0.6100. Min Range: -0.6100

Max Act: 0.4802. Min Act: -0.0001

Data Index: 1436046 (Python Code)

Max Activating Token Index: 436

Text #13

Max Range: 0.6100. Min Range: -0.6100

Max Act: 0.4884. Min Act: -0.0000

Data Index: 1604349 (Python Code)

Max Activating Token Index: 399

Text #14

Max Range: 0.6100. Min Range: -0.6100

Max Act: 0.4779. Min Act: -0.0001

Data Index: 1384845 (Python Code)

Max Activating Token Index: 219

Text #15

Max Range: 0.6100. Min Range: -0.6100

Max Act: 0.4560. Min Act: -0.0001

Data Index: 1578872 (Python Code)

Max Activating Token Index: 208

Text #16

Max Range: 0.6100. Min Range: -0.6100

Max Act: 0.4542. Min Act: -0.0001

Data Index: 1415785 (Python Code)

Max Activating Token Index: 307

Text #17

Max Range: 0.6100. Min Range: -0.6100

Max Act: 0.4515. Min Act: -0.0001

Data Index: 1535493 (Python Code)

Max Activating Token Index: 485

Text #18

Max Range: 0.6100. Min Range: -0.6100

Max Act: 0.4612. Min Act: -0.0001

Data Index: 1465948 (Python Code)

Max Activating Token Index: 132

Text #19

Max Range: 0.6100. Min Range: -0.6100

Max Act: 0.4313. Min Act: -0.0001

Data Index: 1406661 (Python Code)

Max Activating Token Index: 958