Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3250 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.6741. Min Range: -0.6741

Max Act: 0.6741. Min Act: -0.0000

Data Index: 644265 (C4 (Web Text))

Max Activating Token Index: 433

Text #1

Max Range: 0.6741. Min Range: -0.6741

Max Act: 0.6535. Min Act: -0.0000

Data Index: 1061929 (C4 (Web Text))

Max Activating Token Index: 479

Text #2

Max Range: 0.6741. Min Range: -0.6741

Max Act: 0.6260. Min Act: -0.0000

Data Index: 1591962 (Python Code)

Max Activating Token Index: 347

Text #3

Max Range: 0.6741. Min Range: -0.6741

Max Act: 0.6592. Min Act: -0.0000

Data Index: 717989 (C4 (Web Text))

Max Activating Token Index: 358

Text #4

Max Range: 0.6741. Min Range: -0.6741

Max Act: 0.6296. Min Act: -0.0000

Data Index: 1089453 (C4 (Web Text))

Max Activating Token Index: 395

Text #5

Max Range: 0.6741. Min Range: -0.6741

Max Act: 0.6135. Min Act: -0.0000

Data Index: 1331260 (C4 (Web Text))

Max Activating Token Index: 887

Text #6

Max Range: 0.6741. Min Range: -0.6741

Max Act: 0.5451. Min Act: -0.0000

Data Index: 370566 (C4 (Web Text))

Max Activating Token Index: 832

Text #7

Max Range: 0.6741. Min Range: -0.6741

Max Act: 0.6285. Min Act: -0.0000

Data Index: 297214 (C4 (Web Text))

Max Activating Token Index: 654

Text #8

Max Range: 0.6741. Min Range: -0.6741

Max Act: 0.6225. Min Act: -0.0000

Data Index: 1028452 (C4 (Web Text))

Max Activating Token Index: 366

Text #9

Max Range: 0.6741. Min Range: -0.6741

Max Act: 0.5969. Min Act: -0.0000

Data Index: 948221 (C4 (Web Text))

Max Activating Token Index: 438

Text #10

Max Range: 0.6741. Min Range: -0.6741

Max Act: 0.6224. Min Act: -0.0000

Data Index: 251531 (C4 (Web Text))

Max Activating Token Index: 216

Text #11

Max Range: 0.6741. Min Range: -0.6741

Max Act: 0.6375. Min Act: -0.0000

Data Index: 483478 (C4 (Web Text))

Max Activating Token Index: 749

Text #12

Max Range: 0.6741. Min Range: -0.6741

Max Act: 0.5881. Min Act: -0.0000

Data Index: 10569 (C4 (Web Text))

Max Activating Token Index: 448

Text #13

Max Range: 0.6741. Min Range: -0.6741

Max Act: 0.5752. Min Act: -0.0000

Data Index: 660041 (C4 (Web Text))

Max Activating Token Index: 940

Text #14

Max Range: 0.6741. Min Range: -0.6741

Max Act: 0.5749. Min Act: -0.0000

Data Index: 1139506 (C4 (Web Text))

Max Activating Token Index: 936

Text #15

Max Range: 0.6741. Min Range: -0.6741

Max Act: 0.6333. Min Act: -0.0000

Data Index: 236396 (C4 (Web Text))

Max Activating Token Index: 647

Text #16

Max Range: 0.6741. Min Range: -0.6741

Max Act: 0.5364. Min Act: -0.0000

Data Index: 1064167 (C4 (Web Text))

Max Activating Token Index: 886

Text #17

Max Range: 0.6741. Min Range: -0.6741

Max Act: 0.5866. Min Act: -0.0000

Data Index: 55581 (C4 (Web Text))

Max Activating Token Index: 569

Text #18

Max Range: 0.6741. Min Range: -0.6741

Max Act: 0.5282. Min Act: -0.0000

Data Index: 912714 (C4 (Web Text))

Max Activating Token Index: 917

Text #19

Max Range: 0.6741. Min Range: -0.6741

Max Act: 0.6271. Min Act: -0.0000

Data Index: 640820 (C4 (Web Text))

Max Activating Token Index: 401