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

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

Neuron 3262 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7330. Min Range: -0.7330

Max Act: 0.7330. Min Act: -0.0000

Data Index: 704172 (C4 (Web Text))

Max Activating Token Index: 639

Text #1

Max Range: 0.7330. Min Range: -0.7330

Max Act: 0.6308. Min Act: -0.0000

Data Index: 417636 (C4 (Web Text))

Max Activating Token Index: 966

Text #2

Max Range: 0.7330. Min Range: -0.7330

Max Act: 0.5933. Min Act: -0.0000

Data Index: 700586 (C4 (Web Text))

Max Activating Token Index: 549

Text #3

Max Range: 0.7330. Min Range: -0.7330

Max Act: 0.5356. Min Act: -0.0000

Data Index: 481174 (C4 (Web Text))

Max Activating Token Index: 758

Text #4

Max Range: 0.7330. Min Range: -0.7330

Max Act: 0.5073. Min Act: -0.0000

Data Index: 472012 (C4 (Web Text))

Max Activating Token Index: 767

Text #5

Max Range: 0.7330. Min Range: -0.7330

Max Act: 0.5271. Min Act: -0.0000

Data Index: 355769 (C4 (Web Text))

Max Activating Token Index: 742

Text #6

Max Range: 0.7330. Min Range: -0.7330

Max Act: 0.4775. Min Act: -0.0000

Data Index: 777879 (C4 (Web Text))

Max Activating Token Index: 668

Text #7

Max Range: 0.7330. Min Range: -0.7330

Max Act: 0.4628. Min Act: -0.0000

Data Index: 418638 (C4 (Web Text))

Max Activating Token Index: 707

Text #8

Max Range: 0.7330. Min Range: -0.7330

Max Act: 0.4993. Min Act: -0.0000

Data Index: 1166782 (C4 (Web Text))

Max Activating Token Index: 569

Text #9

Max Range: 0.7330. Min Range: -0.7330

Max Act: 0.4778. Min Act: -0.0000

Data Index: 382105 (C4 (Web Text))

Max Activating Token Index: 126

Text #10

Max Range: 0.7330. Min Range: -0.7330

Max Act: 0.4589. Min Act: -0.0000

Data Index: 382132 (C4 (Web Text))

Max Activating Token Index: 102

Text #11

Max Range: 0.7330. Min Range: -0.7330

Max Act: 0.5043. Min Act: -0.0000

Data Index: 910336 (C4 (Web Text))

Max Activating Token Index: 205

Text #12

Max Range: 0.7330. Min Range: -0.7330

Max Act: 0.4540. Min Act: -0.0000

Data Index: 1101535 (C4 (Web Text))

Max Activating Token Index: 678

Text #13

Max Range: 0.7330. Min Range: -0.7330

Max Act: 0.4174. Min Act: -0.0000

Data Index: 993745 (C4 (Web Text))

Max Activating Token Index: 775

Text #14

Max Range: 0.7330. Min Range: -0.7330

Max Act: 0.4332. Min Act: -0.0000

Data Index: 1253330 (C4 (Web Text))

Max Activating Token Index: 205

Text #15

Max Range: 0.7330. Min Range: -0.7330

Max Act: 0.4431. Min Act: -0.0000

Data Index: 242042 (C4 (Web Text))

Max Activating Token Index: 980

Text #16

Max Range: 0.7330. Min Range: -0.7330

Max Act: 0.3889. Min Act: -0.0000

Data Index: 639449 (C4 (Web Text))

Max Activating Token Index: 309

Text #17

Max Range: 0.7330. Min Range: -0.7330

Max Act: 0.4198. Min Act: -0.0000

Data Index: 176607 (C4 (Web Text))

Max Activating Token Index: 16

Text #18

Max Range: 0.7330. Min Range: -0.7330

Max Act: 0.4058. Min Act: -0.0000

Data Index: 529889 (C4 (Web Text))

Max Activating Token Index: 619

Text #19

Max Range: 0.7330. Min Range: -0.7330

Max Act: 0.4291. Min Act: -0.0000

Data Index: 312170 (C4 (Web Text))

Max Activating Token Index: 26