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

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

Neuron 1768 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5958. Min Range: -0.5958

Max Act: 0.5958. Min Act: -0.0000

Data Index: 284169 (C4 (Web Text))

Max Activating Token Index: 285

Text #1

Max Range: 0.5958. Min Range: -0.5958

Max Act: 0.5761. Min Act: -0.0000

Data Index: 371179 (C4 (Web Text))

Max Activating Token Index: 571

Text #2

Max Range: 0.5958. Min Range: -0.5958

Max Act: 0.5872. Min Act: -0.0000

Data Index: 668210 (C4 (Web Text))

Max Activating Token Index: 544

Text #3

Max Range: 0.5958. Min Range: -0.5958

Max Act: 0.5613. Min Act: -0.0000

Data Index: 903137 (C4 (Web Text))

Max Activating Token Index: 491

Text #4

Max Range: 0.5958. Min Range: -0.5958

Max Act: 0.5633. Min Act: -0.0000

Data Index: 1206143 (C4 (Web Text))

Max Activating Token Index: 471

Text #5

Max Range: 0.5958. Min Range: -0.5958

Max Act: 0.5545. Min Act: -0.0000

Data Index: 839401 (C4 (Web Text))

Max Activating Token Index: 551

Text #6

Max Range: 0.5958. Min Range: -0.5958

Max Act: 0.5430. Min Act: -0.0000

Data Index: 127701 (C4 (Web Text))

Max Activating Token Index: 509

Text #7

Max Range: 0.5958. Min Range: -0.5958

Max Act: 0.5246. Min Act: -0.0000

Data Index: 1116054 (C4 (Web Text))

Max Activating Token Index: 492

Text #8

Max Range: 0.5958. Min Range: -0.5958

Max Act: 0.5196. Min Act: -0.0000

Data Index: 242225 (C4 (Web Text))

Max Activating Token Index: 513

Text #9

Max Range: 0.5958. Min Range: -0.5958

Max Act: 0.4865. Min Act: -0.0000

Data Index: 1122725 (C4 (Web Text))

Max Activating Token Index: 874

Text #10

Max Range: 0.5958. Min Range: -0.5958

Max Act: 0.4824. Min Act: -0.0000

Data Index: 915604 (C4 (Web Text))

Max Activating Token Index: 581

Text #11

Max Range: 0.5958. Min Range: -0.5958

Max Act: 0.5154. Min Act: -0.0000

Data Index: 1262107 (C4 (Web Text))

Max Activating Token Index: 894

Text #12

Max Range: 0.5958. Min Range: -0.5958

Max Act: 0.5130. Min Act: -0.0000

Data Index: 214873 (C4 (Web Text))

Max Activating Token Index: 586

Text #13

Max Range: 0.5958. Min Range: -0.5958

Max Act: 0.4829. Min Act: -0.0000

Data Index: 56104 (C4 (Web Text))

Max Activating Token Index: 158

Text #14

Max Range: 0.5958. Min Range: -0.5958

Max Act: 0.4625. Min Act: -0.0000

Data Index: 725917 (C4 (Web Text))

Max Activating Token Index: 544

Text #15

Max Range: 0.5958. Min Range: -0.5958

Max Act: 0.4641. Min Act: -0.0000

Data Index: 816770 (C4 (Web Text))

Max Activating Token Index: 622

Text #16

Max Range: 0.5958. Min Range: -0.5958

Max Act: 0.4570. Min Act: -0.0000

Data Index: 1250789 (C4 (Web Text))

Max Activating Token Index: 93

Text #17

Max Range: 0.5958. Min Range: -0.5958

Max Act: 0.5013. Min Act: -0.0000

Data Index: 574446 (C4 (Web Text))

Max Activating Token Index: 785

Text #18

Max Range: 0.5958. Min Range: -0.5958

Max Act: 0.4492. Min Act: -0.0000

Data Index: 669855 (C4 (Web Text))

Max Activating Token Index: 305

Text #19

Max Range: 0.5958. Min Range: -0.5958

Max Act: 0.4317. Min Act: -0.0000

Data Index: 708629 (C4 (Web Text))

Max Activating Token Index: 729