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

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

Neuron 937 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5243. Min Range: -0.5243

Max Act: 0.4561. Min Act: -0.0000

Data Index: 944280 (C4 (Web Text))

Max Activating Token Index: 597

Text #1

Max Range: 0.5243. Min Range: -0.5243

Max Act: 0.4910. Min Act: -0.0000

Data Index: 566977 (C4 (Web Text))

Max Activating Token Index: 299

Text #2

Max Range: 0.5243. Min Range: -0.5243

Max Act: 0.4849. Min Act: -0.0000

Data Index: 901853 (C4 (Web Text))

Max Activating Token Index: 263

Text #3

Max Range: 0.5243. Min Range: -0.5243

Max Act: 0.4502. Min Act: -0.0000

Data Index: 566114 (C4 (Web Text))

Max Activating Token Index: 323

Text #4

Max Range: 0.5243. Min Range: -0.5243

Max Act: 0.4340. Min Act: -0.0000

Data Index: 1272949 (C4 (Web Text))

Max Activating Token Index: 818

Text #5

Max Range: 0.5243. Min Range: -0.5243

Max Act: 0.5243. Min Act: -0.0000

Data Index: 653026 (C4 (Web Text))

Max Activating Token Index: 875

Text #6

Max Range: 0.5243. Min Range: -0.5243

Max Act: 0.4455. Min Act: -0.0000

Data Index: 272495 (C4 (Web Text))

Max Activating Token Index: 332

Text #7

Max Range: 0.5243. Min Range: -0.5243

Max Act: 0.4240. Min Act: 0.0000

Data Index: 981917 (C4 (Web Text))

Max Activating Token Index: 445

Text #8

Max Range: 0.5243. Min Range: -0.5243

Max Act: 0.3867. Min Act: -0.0000

Data Index: 1052292 (C4 (Web Text))

Max Activating Token Index: 750

Text #9

Max Range: 0.5243. Min Range: -0.5243

Max Act: 0.4073. Min Act: -0.0000

Data Index: 29468 (C4 (Web Text))

Max Activating Token Index: 761

Text #10

Max Range: 0.5243. Min Range: -0.5243

Max Act: 0.4114. Min Act: -0.0000

Data Index: 690124 (C4 (Web Text))

Max Activating Token Index: 251

Text #11

Max Range: 0.5243. Min Range: -0.5243

Max Act: 0.4139. Min Act: -0.0000

Data Index: 821987 (C4 (Web Text))

Max Activating Token Index: 995

Text #12

Max Range: 0.5243. Min Range: -0.5243

Max Act: 0.3324. Min Act: -0.0000

Data Index: 932948 (C4 (Web Text))

Max Activating Token Index: 266

Text #13

Max Range: 0.5243. Min Range: -0.5243

Max Act: 0.3830. Min Act: -0.0000

Data Index: 228051 (C4 (Web Text))

Max Activating Token Index: 395

Text #14

Max Range: 0.5243. Min Range: -0.5243

Max Act: 0.3840. Min Act: -0.0000

Data Index: 849640 (C4 (Web Text))

Max Activating Token Index: 193

Text #15

Max Range: 0.5243. Min Range: -0.5243

Max Act: 0.3839. Min Act: -0.0000

Data Index: 983821 (C4 (Web Text))

Max Activating Token Index: 1004

Text #16

Max Range: 0.5243. Min Range: -0.5243

Max Act: 0.3480. Min Act: -0.0000

Data Index: 1271436 (C4 (Web Text))

Max Activating Token Index: 306

Text #17

Max Range: 0.5243. Min Range: -0.5243

Max Act: 0.3476. Min Act: -0.0000

Data Index: 378949 (C4 (Web Text))

Max Activating Token Index: 396

Text #18

Max Range: 0.5243. Min Range: -0.5243

Max Act: 0.3566. Min Act: -0.0000

Data Index: 198652 (C4 (Web Text))

Max Activating Token Index: 831

Text #19

Max Range: 0.5243. Min Range: -0.5243

Max Act: 0.3713. Min Act: -0.0000

Data Index: 275994 (C4 (Web Text))

Max Activating Token Index: 941