Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 802 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 3.2459. Min Range: -3.2459

Max Act: 3.0658. Min Act: -0.0000

Data Index: 920562 (C4 (Web Text))

Max Activating Token Index: 74

Text #1

Max Range: 3.2459. Min Range: -3.2459

Max Act: 2.9125. Min Act: -0.0000

Data Index: 252181 (C4 (Web Text))

Max Activating Token Index: 149

Text #2

Max Range: 3.2459. Min Range: -3.2459

Max Act: 3.2459. Min Act: -0.0000

Data Index: 1013995 (C4 (Web Text))

Max Activating Token Index: 132

Text #3

Max Range: 3.2459. Min Range: -3.2459

Max Act: 2.7539. Min Act: -0.0000

Data Index: 1275427 (C4 (Web Text))

Max Activating Token Index: 128

Text #4

Max Range: 3.2459. Min Range: -3.2459

Max Act: 2.4534. Min Act: -0.0001

Data Index: 41283 (C4 (Web Text))

Max Activating Token Index: 242

Text #5

Max Range: 3.2459. Min Range: -3.2459

Max Act: 2.8140. Min Act: -0.0000

Data Index: 1029966 (C4 (Web Text))

Max Activating Token Index: 59

Text #6

Max Range: 3.2459. Min Range: -3.2459

Max Act: 2.4719. Min Act: -0.0000

Data Index: 1117682 (C4 (Web Text))

Max Activating Token Index: 717

Text #7

Max Range: 3.2459. Min Range: -3.2459

Max Act: 2.6808. Min Act: -0.0001

Data Index: 465218 (C4 (Web Text))

Max Activating Token Index: 177

Text #8

Max Range: 3.2459. Min Range: -3.2459

Max Act: 2.4423. Min Act: -0.0000

Data Index: 609057 (C4 (Web Text))

Max Activating Token Index: 882

Text #9

Max Range: 3.2459. Min Range: -3.2459

Max Act: 2.3330. Min Act: -0.0000

Data Index: 990768 (C4 (Web Text))

Max Activating Token Index: 181

Text #10

Max Range: 3.2459. Min Range: -3.2459

Max Act: 2.2226. Min Act: -0.0000

Data Index: 1148016 (C4 (Web Text))

Max Activating Token Index: 839

Text #11

Max Range: 3.2459. Min Range: -3.2459

Max Act: 2.2707. Min Act: -0.0000

Data Index: 36358 (C4 (Web Text))

Max Activating Token Index: 298

Text #12

Max Range: 3.2459. Min Range: -3.2459

Max Act: 1.9594. Min Act: -0.0001

Data Index: 1358282 (C4 (Web Text))

Max Activating Token Index: 213

Text #13

Max Range: 3.2459. Min Range: -3.2459

Max Act: 2.1829. Min Act: -0.0000

Data Index: 417082 (C4 (Web Text))

Max Activating Token Index: 147

Text #14

Max Range: 3.2459. Min Range: -3.2459

Max Act: 2.0265. Min Act: -0.0001

Data Index: 1260345 (C4 (Web Text))

Max Activating Token Index: 870

Text #15

Max Range: 3.2459. Min Range: -3.2459

Max Act: 2.0512. Min Act: -0.0000

Data Index: 1102232 (C4 (Web Text))

Max Activating Token Index: 481

Text #16

Max Range: 3.2459. Min Range: -3.2459

Max Act: 1.9621. Min Act: -0.0001

Data Index: 131426 (C4 (Web Text))

Max Activating Token Index: 898

Text #17

Max Range: 3.2459. Min Range: -3.2459

Max Act: 1.8400. Min Act: -0.0000

Data Index: 474218 (C4 (Web Text))

Max Activating Token Index: 35

Text #18

Max Range: 3.2459. Min Range: -3.2459

Max Act: 1.9477. Min Act: -0.0000

Data Index: 172175 (C4 (Web Text))

Max Activating Token Index: 321

Text #19

Max Range: 3.2459. Min Range: -3.2459

Max Act: 1.9736. Min Act: -0.0000

Data Index: 627926 (C4 (Web Text))

Max Activating Token Index: 275