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

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

Neuron 1127 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: 2.7255. Min Range: -2.7255

Max Act: 2.6253. Min Act: -0.0000

Data Index: 745188 (C4 (Web Text))

Max Activating Token Index: 347

Text #1

Max Range: 2.7255. Min Range: -2.7255

Max Act: 2.7255. Min Act: -0.0000

Data Index: 240959 (C4 (Web Text))

Max Activating Token Index: 554

Text #2

Max Range: 2.7255. Min Range: -2.7255

Max Act: 2.4199. Min Act: -0.0000

Data Index: 415484 (C4 (Web Text))

Max Activating Token Index: 412

Text #3

Max Range: 2.7255. Min Range: -2.7255

Max Act: 2.5156. Min Act: -0.0000

Data Index: 223358 (C4 (Web Text))

Max Activating Token Index: 393

Text #4

Max Range: 2.7255. Min Range: -2.7255

Max Act: 2.4209. Min Act: -0.0000

Data Index: 507690 (C4 (Web Text))

Max Activating Token Index: 574

Text #5

Max Range: 2.7255. Min Range: -2.7255

Max Act: 2.2860. Min Act: -0.0000

Data Index: 1077805 (C4 (Web Text))

Max Activating Token Index: 827

Text #6

Max Range: 2.7255. Min Range: -2.7255

Max Act: 2.2894. Min Act: -0.0000

Data Index: 416516 (C4 (Web Text))

Max Activating Token Index: 219

Text #7

Max Range: 2.7255. Min Range: -2.7255

Max Act: 2.1517. Min Act: -0.0000

Data Index: 1021717 (C4 (Web Text))

Max Activating Token Index: 679

Text #8

Max Range: 2.7255. Min Range: -2.7255

Max Act: 2.4070. Min Act: -0.0000

Data Index: 452529 (C4 (Web Text))

Max Activating Token Index: 218

Text #9

Max Range: 2.7255. Min Range: -2.7255

Max Act: 2.3231. Min Act: -0.0000

Data Index: 1071520 (C4 (Web Text))

Max Activating Token Index: 378

Text #10

Max Range: 2.7255. Min Range: -2.7255

Max Act: 2.3711. Min Act: -0.0000

Data Index: 1197520 (C4 (Web Text))

Max Activating Token Index: 297

Text #11

Max Range: 2.7255. Min Range: -2.7255

Max Act: 2.4735. Min Act: -0.0000

Data Index: 183718 (C4 (Web Text))

Max Activating Token Index: 411

Text #12

Max Range: 2.7255. Min Range: -2.7255

Max Act: 2.1896. Min Act: -0.0000

Data Index: 119110 (C4 (Web Text))

Max Activating Token Index: 840

Text #13

Max Range: 2.7255. Min Range: -2.7255

Max Act: 2.4799. Min Act: -0.0000

Data Index: 476800 (C4 (Web Text))

Max Activating Token Index: 374

Text #14

Max Range: 2.7255. Min Range: -2.7255

Max Act: 2.3128. Min Act: -0.0000

Data Index: 563906 (C4 (Web Text))

Max Activating Token Index: 335

Text #15

Max Range: 2.7255. Min Range: -2.7255

Max Act: 2.2978. Min Act: -0.0000

Data Index: 941274 (C4 (Web Text))

Max Activating Token Index: 827

Text #16

Max Range: 2.7255. Min Range: -2.7255

Max Act: 2.2782. Min Act: -0.0000

Data Index: 1206354 (C4 (Web Text))

Max Activating Token Index: 550

Text #17

Max Range: 2.7255. Min Range: -2.7255

Max Act: 2.3143. Min Act: -0.0000

Data Index: 2524 (C4 (Web Text))

Max Activating Token Index: 844

Text #18

Max Range: 2.7255. Min Range: -2.7255

Max Act: 2.1628. Min Act: -0.0000

Data Index: 849871 (C4 (Web Text))

Max Activating Token Index: 722

Text #19

Max Range: 2.7255. Min Range: -2.7255

Max Act: 2.3130. Min Act: -0.0000

Data Index: 284950 (C4 (Web Text))

Max Activating Token Index: 639