Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 724 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.7265. Min Range: -0.7265

Max Act: 0.7265. Min Act: -0.0003

Data Index: 175286 (C4 (Web Text))

Max Activating Token Index: 160

Text #1

Max Range: 0.7265. Min Range: -0.7265

Max Act: 0.6013. Min Act: -0.0003

Data Index: 1293632 (C4 (Web Text))

Max Activating Token Index: 838

Text #2

Max Range: 0.7265. Min Range: -0.7265

Max Act: 0.5887. Min Act: -0.0003

Data Index: 164128 (C4 (Web Text))

Max Activating Token Index: 341

Text #3

Max Range: 0.7265. Min Range: -0.7265

Max Act: 0.5790. Min Act: -0.0003

Data Index: 479922 (C4 (Web Text))

Max Activating Token Index: 516

Text #4

Max Range: 0.7265. Min Range: -0.7265

Max Act: 0.5522. Min Act: -0.0003

Data Index: 231648 (C4 (Web Text))

Max Activating Token Index: 451

Text #5

Max Range: 0.7265. Min Range: -0.7265

Max Act: 0.5477. Min Act: -0.0002

Data Index: 800457 (C4 (Web Text))

Max Activating Token Index: 351

Text #6

Max Range: 0.7265. Min Range: -0.7265

Max Act: 0.5219. Min Act: -0.0003

Data Index: 1283259 (C4 (Web Text))

Max Activating Token Index: 646

Text #7

Max Range: 0.7265. Min Range: -0.7265

Max Act: 0.5011. Min Act: -0.0003

Data Index: 1017450 (C4 (Web Text))

Max Activating Token Index: 862

Text #8

Max Range: 0.7265. Min Range: -0.7265

Max Act: 0.5111. Min Act: -0.0003

Data Index: 985921 (C4 (Web Text))

Max Activating Token Index: 643

Text #9

Max Range: 0.7265. Min Range: -0.7265

Max Act: 0.5282. Min Act: -0.0003

Data Index: 166387 (C4 (Web Text))

Max Activating Token Index: 19

Text #10

Max Range: 0.7265. Min Range: -0.7265

Max Act: 0.5160. Min Act: -0.0003

Data Index: 1093470 (C4 (Web Text))

Max Activating Token Index: 400

Text #11

Max Range: 0.7265. Min Range: -0.7265

Max Act: 0.5815. Min Act: -0.0003

Data Index: 814538 (C4 (Web Text))

Max Activating Token Index: 808

Text #12

Max Range: 0.7265. Min Range: -0.7265

Max Act: 0.5044. Min Act: -0.0003

Data Index: 611140 (C4 (Web Text))

Max Activating Token Index: 540

Text #13

Max Range: 0.7265. Min Range: -0.7265

Max Act: 0.5042. Min Act: -0.0003

Data Index: 598961 (C4 (Web Text))

Max Activating Token Index: 599

Text #14

Max Range: 0.7265. Min Range: -0.7265

Max Act: 0.5519. Min Act: -0.0003

Data Index: 84711 (C4 (Web Text))

Max Activating Token Index: 911

Text #15

Max Range: 0.7265. Min Range: -0.7265

Max Act: 0.4787. Min Act: -0.0003

Data Index: 977429 (C4 (Web Text))

Max Activating Token Index: 620

Text #16

Max Range: 0.7265. Min Range: -0.7265

Max Act: 0.4637. Min Act: -0.0003

Data Index: 829008 (C4 (Web Text))

Max Activating Token Index: 294

Text #17

Max Range: 0.7265. Min Range: -0.7265

Max Act: 0.4716. Min Act: -0.0003

Data Index: 1310494 (C4 (Web Text))

Max Activating Token Index: 725

Text #18

Max Range: 0.7265. Min Range: -0.7265

Max Act: 0.4687. Min Act: -0.0003

Data Index: 134667 (C4 (Web Text))

Max Activating Token Index: 338

Text #19

Max Range: 0.7265. Min Range: -0.7265

Max Act: 0.4714. Min Act: -0.0003

Data Index: 1325370 (C4 (Web Text))

Max Activating Token Index: 710