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

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

Neuron 2845 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: 0.6394. Min Range: -0.6394

Max Act: 0.6394. Min Act: -0.0000

Data Index: 964097 (C4 (Web Text))

Max Activating Token Index: 323

Text #1

Max Range: 0.6394. Min Range: -0.6394

Max Act: 0.6121. Min Act: -0.0000

Data Index: 967238 (C4 (Web Text))

Max Activating Token Index: 91

Text #2

Max Range: 0.6394. Min Range: -0.6394

Max Act: 0.5067. Min Act: -0.0000

Data Index: 946090 (C4 (Web Text))

Max Activating Token Index: 809

Text #3

Max Range: 0.6394. Min Range: -0.6394

Max Act: 0.5648. Min Act: -0.0000

Data Index: 271787 (C4 (Web Text))

Max Activating Token Index: 871

Text #4

Max Range: 0.6394. Min Range: -0.6394

Max Act: 0.5142. Min Act: 0.0000

Data Index: 525121 (C4 (Web Text))

Max Activating Token Index: 893

Text #5

Max Range: 0.6394. Min Range: -0.6394

Max Act: 0.5293. Min Act: -0.0000

Data Index: 673750 (C4 (Web Text))

Max Activating Token Index: 436

Text #6

Max Range: 0.6394. Min Range: -0.6394

Max Act: 0.5322. Min Act: -0.0000

Data Index: 1348536 (C4 (Web Text))

Max Activating Token Index: 335

Text #7

Max Range: 0.6394. Min Range: -0.6394

Max Act: 0.5249. Min Act: 0.0000

Data Index: 954384 (C4 (Web Text))

Max Activating Token Index: 166

Text #8

Max Range: 0.6394. Min Range: -0.6394

Max Act: 0.5202. Min Act: -0.0000

Data Index: 1247848 (C4 (Web Text))

Max Activating Token Index: 770

Text #9

Max Range: 0.6394. Min Range: -0.6394

Max Act: 0.5279. Min Act: -0.0000

Data Index: 1195336 (C4 (Web Text))

Max Activating Token Index: 222

Text #10

Max Range: 0.6394. Min Range: -0.6394

Max Act: 0.5134. Min Act: -0.0000

Data Index: 753471 (C4 (Web Text))

Max Activating Token Index: 653

Text #11

Max Range: 0.6394. Min Range: -0.6394

Max Act: 0.4870. Min Act: -0.0000

Data Index: 790738 (C4 (Web Text))

Max Activating Token Index: 122

Text #12

Max Range: 0.6394. Min Range: -0.6394

Max Act: 0.4894. Min Act: -0.0000

Data Index: 397684 (C4 (Web Text))

Max Activating Token Index: 16

Text #13

Max Range: 0.6394. Min Range: -0.6394

Max Act: 0.4577. Min Act: -0.0000

Data Index: 189549 (C4 (Web Text))

Max Activating Token Index: 635

Text #14

Max Range: 0.6394. Min Range: -0.6394

Max Act: 0.4831. Min Act: -0.0000

Data Index: 455184 (C4 (Web Text))

Max Activating Token Index: 103

Text #15

Max Range: 0.6394. Min Range: -0.6394

Max Act: 0.4994. Min Act: -0.0000

Data Index: 792519 (C4 (Web Text))

Max Activating Token Index: 169

Text #16

Max Range: 0.6394. Min Range: -0.6394

Max Act: 0.4756. Min Act: 0.0000

Data Index: 1013556 (C4 (Web Text))

Max Activating Token Index: 199

Text #17

Max Range: 0.6394. Min Range: -0.6394

Max Act: 0.4669. Min Act: -0.0000

Data Index: 528656 (C4 (Web Text))

Max Activating Token Index: 800

Text #18

Max Range: 0.6394. Min Range: -0.6394

Max Act: 0.4657. Min Act: -0.0000

Data Index: 951625 (C4 (Web Text))

Max Activating Token Index: 176

Text #19

Max Range: 0.6394. Min Range: -0.6394

Max Act: 0.5262. Min Act: -0.0000

Data Index: 1041951 (C4 (Web Text))

Max Activating Token Index: 25