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

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

Neuron 3316 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: 0.5658. Min Range: -0.5658

Max Act: 0.5658. Min Act: -0.0000

Data Index: 824467 (C4 (Web Text))

Max Activating Token Index: 46

Text #1

Max Range: 0.5658. Min Range: -0.5658

Max Act: 0.5366. Min Act: -0.0000

Data Index: 924608 (C4 (Web Text))

Max Activating Token Index: 493

Text #2

Max Range: 0.5658. Min Range: -0.5658

Max Act: 0.4936. Min Act: -0.0000

Data Index: 924740 (C4 (Web Text))

Max Activating Token Index: 1000

Text #3

Max Range: 0.5658. Min Range: -0.5658

Max Act: 0.5254. Min Act: -0.0000

Data Index: 1087901 (C4 (Web Text))

Max Activating Token Index: 623

Text #4

Max Range: 0.5658. Min Range: -0.5658

Max Act: 0.4922. Min Act: -0.0000

Data Index: 197758 (C4 (Web Text))

Max Activating Token Index: 824

Text #5

Max Range: 0.5658. Min Range: -0.5658

Max Act: 0.5067. Min Act: -0.0000

Data Index: 223805 (C4 (Web Text))

Max Activating Token Index: 660

Text #6

Max Range: 0.5658. Min Range: -0.5658

Max Act: 0.4761. Min Act: 0.0000

Data Index: 1250942 (C4 (Web Text))

Max Activating Token Index: 927

Text #7

Max Range: 0.5658. Min Range: -0.5658

Max Act: 0.4689. Min Act: -0.0000

Data Index: 1306866 (C4 (Web Text))

Max Activating Token Index: 271

Text #8

Max Range: 0.5658. Min Range: -0.5658

Max Act: 0.4825. Min Act: -0.0000

Data Index: 1205241 (C4 (Web Text))

Max Activating Token Index: 444

Text #9

Max Range: 0.5658. Min Range: -0.5658

Max Act: 0.4806. Min Act: -0.0000

Data Index: 944177 (C4 (Web Text))

Max Activating Token Index: 325

Text #10

Max Range: 0.5658. Min Range: -0.5658

Max Act: 0.4949. Min Act: -0.0000

Data Index: 1062550 (C4 (Web Text))

Max Activating Token Index: 898

Text #11

Max Range: 0.5658. Min Range: -0.5658

Max Act: 0.4635. Min Act: -0.0000

Data Index: 84345 (C4 (Web Text))

Max Activating Token Index: 1003

Text #12

Max Range: 0.5658. Min Range: -0.5658

Max Act: 0.4732. Min Act: -0.0000

Data Index: 435752 (C4 (Web Text))

Max Activating Token Index: 588

Text #13

Max Range: 0.5658. Min Range: -0.5658

Max Act: 0.4689. Min Act: -0.0000

Data Index: 1076431 (C4 (Web Text))

Max Activating Token Index: 654

Text #14

Max Range: 0.5658. Min Range: -0.5658

Max Act: 0.4828. Min Act: -0.0000

Data Index: 158321 (C4 (Web Text))

Max Activating Token Index: 90

Text #15

Max Range: 0.5658. Min Range: -0.5658

Max Act: 0.4568. Min Act: -0.0000

Data Index: 941072 (C4 (Web Text))

Max Activating Token Index: 455

Text #16

Max Range: 0.5658. Min Range: -0.5658

Max Act: 0.4450. Min Act: -0.0000

Data Index: 387564 (C4 (Web Text))

Max Activating Token Index: 499

Text #17

Max Range: 0.5658. Min Range: -0.5658

Max Act: 0.4312. Min Act: -0.0000

Data Index: 463393 (C4 (Web Text))

Max Activating Token Index: 236

Text #18

Max Range: 0.5658. Min Range: -0.5658

Max Act: 0.4241. Min Act: -0.0000

Data Index: 779045 (C4 (Web Text))

Max Activating Token Index: 126

Text #19

Max Range: 0.5658. Min Range: -0.5658

Max Act: 0.4391. Min Act: -0.0000

Data Index: 475631 (C4 (Web Text))

Max Activating Token Index: 668