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

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

Neuron 3054 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9162. Min Range: -1.9162

Max Act: 1.9162. Min Act: -0.0000

Data Index: 708354 (C4 (Web Text))

Max Activating Token Index: 146

Text #1

Max Range: 1.9162. Min Range: -1.9162

Max Act: 1.7808. Min Act: -0.0000

Data Index: 393371 (C4 (Web Text))

Max Activating Token Index: 928

Text #2

Max Range: 1.9162. Min Range: -1.9162

Max Act: 1.6954. Min Act: -0.0000

Data Index: 1257602 (C4 (Web Text))

Max Activating Token Index: 682

Text #3

Max Range: 1.9162. Min Range: -1.9162

Max Act: 1.5744. Min Act: -0.0000

Data Index: 232380 (C4 (Web Text))

Max Activating Token Index: 333

Text #4

Max Range: 1.9162. Min Range: -1.9162

Max Act: 1.4220. Min Act: -0.0000

Data Index: 1168702 (C4 (Web Text))

Max Activating Token Index: 170

Text #5

Max Range: 1.9162. Min Range: -1.9162

Max Act: 1.4382. Min Act: -0.0000

Data Index: 748558 (C4 (Web Text))

Max Activating Token Index: 900

Text #6

Max Range: 1.9162. Min Range: -1.9162

Max Act: 1.3244. Min Act: -0.0000

Data Index: 417543 (C4 (Web Text))

Max Activating Token Index: 411

Text #7

Max Range: 1.9162. Min Range: -1.9162

Max Act: 1.4434. Min Act: -0.0000

Data Index: 564295 (C4 (Web Text))

Max Activating Token Index: 767

Text #8

Max Range: 1.9162. Min Range: -1.9162

Max Act: 1.5237. Min Act: -0.0000

Data Index: 482407 (C4 (Web Text))

Max Activating Token Index: 598

Text #9

Max Range: 1.9162. Min Range: -1.9162

Max Act: 1.4585. Min Act: -0.0000

Data Index: 389111 (C4 (Web Text))

Max Activating Token Index: 381

Text #10

Max Range: 1.9162. Min Range: -1.9162

Max Act: 1.5183. Min Act: -0.0000

Data Index: 1063079 (C4 (Web Text))

Max Activating Token Index: 700

Text #11

Max Range: 1.9162. Min Range: -1.9162

Max Act: 1.4330. Min Act: -0.0000

Data Index: 86483 (C4 (Web Text))

Max Activating Token Index: 463

Text #12

Max Range: 1.9162. Min Range: -1.9162

Max Act: 1.3781. Min Act: -0.0000

Data Index: 265579 (C4 (Web Text))

Max Activating Token Index: 610

Text #13

Max Range: 1.9162. Min Range: -1.9162

Max Act: 1.3382. Min Act: -0.0000

Data Index: 265992 (C4 (Web Text))

Max Activating Token Index: 623

Text #14

Max Range: 1.9162. Min Range: -1.9162

Max Act: 1.3386. Min Act: -0.0000

Data Index: 1193165 (C4 (Web Text))

Max Activating Token Index: 299

Text #15

Max Range: 1.9162. Min Range: -1.9162

Max Act: 1.3860. Min Act: -0.0000

Data Index: 658409 (C4 (Web Text))

Max Activating Token Index: 428

Text #16

Max Range: 1.9162. Min Range: -1.9162

Max Act: 1.3277. Min Act: -0.0000

Data Index: 1265163 (C4 (Web Text))

Max Activating Token Index: 479

Text #17

Max Range: 1.9162. Min Range: -1.9162

Max Act: 1.3306. Min Act: -0.0000

Data Index: 900338 (C4 (Web Text))

Max Activating Token Index: 194

Text #18

Max Range: 1.9162. Min Range: -1.9162

Max Act: 1.2893. Min Act: -0.0000

Data Index: 416446 (C4 (Web Text))

Max Activating Token Index: 465

Text #19

Max Range: 1.9162. Min Range: -1.9162

Max Act: 1.2861. Min Act: -0.0000

Data Index: 534792 (C4 (Web Text))

Max Activating Token Index: 1005