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

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

Neuron 672 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7436. Min Range: -1.7436

Max Act: 1.7436. Min Act: -0.0001

Data Index: 1067948 (C4 (Web Text))

Max Activating Token Index: 601

Text #1

Max Range: 1.7436. Min Range: -1.7436

Max Act: 1.5135. Min Act: -0.0001

Data Index: 243176 (C4 (Web Text))

Max Activating Token Index: 824

Text #2

Max Range: 1.7436. Min Range: -1.7436

Max Act: 1.4050. Min Act: -0.0001

Data Index: 1258448 (C4 (Web Text))

Max Activating Token Index: 596

Text #3

Max Range: 1.7436. Min Range: -1.7436

Max Act: 1.4827. Min Act: -0.0001

Data Index: 386394 (C4 (Web Text))

Max Activating Token Index: 134

Text #4

Max Range: 1.7436. Min Range: -1.7436

Max Act: 1.3830. Min Act: -0.0001

Data Index: 842950 (C4 (Web Text))

Max Activating Token Index: 298

Text #5

Max Range: 1.7436. Min Range: -1.7436

Max Act: 1.2682. Min Act: -0.0001

Data Index: 1351283 (C4 (Web Text))

Max Activating Token Index: 242

Text #6

Max Range: 1.7436. Min Range: -1.7436

Max Act: 1.2679. Min Act: -0.0001

Data Index: 954706 (C4 (Web Text))

Max Activating Token Index: 491

Text #7

Max Range: 1.7436. Min Range: -1.7436

Max Act: 1.2297. Min Act: -0.0001

Data Index: 559435 (C4 (Web Text))

Max Activating Token Index: 59

Text #8

Max Range: 1.7436. Min Range: -1.7436

Max Act: 1.2537. Min Act: -0.0001

Data Index: 232438 (C4 (Web Text))

Max Activating Token Index: 500

Text #9

Max Range: 1.7436. Min Range: -1.7436

Max Act: 1.2000. Min Act: -0.0001

Data Index: 731521 (C4 (Web Text))

Max Activating Token Index: 371

Text #10

Max Range: 1.7436. Min Range: -1.7436

Max Act: 1.1966. Min Act: -0.0001

Data Index: 917192 (C4 (Web Text))

Max Activating Token Index: 361

Text #11

Max Range: 1.7436. Min Range: -1.7436

Max Act: 1.2670. Min Act: -0.0001

Data Index: 555209 (C4 (Web Text))

Max Activating Token Index: 155

Text #12

Max Range: 1.7436. Min Range: -1.7436

Max Act: 1.2563. Min Act: -0.0001

Data Index: 650865 (C4 (Web Text))

Max Activating Token Index: 362

Text #13

Max Range: 1.7436. Min Range: -1.7436

Max Act: 1.2514. Min Act: -0.0001

Data Index: 319783 (C4 (Web Text))

Max Activating Token Index: 762

Text #14

Max Range: 1.7436. Min Range: -1.7436

Max Act: 1.1867. Min Act: -0.0001

Data Index: 1085029 (C4 (Web Text))

Max Activating Token Index: 900

Text #15

Max Range: 1.7436. Min Range: -1.7436

Max Act: 1.1752. Min Act: -0.0001

Data Index: 1227382 (C4 (Web Text))

Max Activating Token Index: 846

Text #16

Max Range: 1.7436. Min Range: -1.7436

Max Act: 1.1650. Min Act: -0.0001

Data Index: 932183 (C4 (Web Text))

Max Activating Token Index: 479

Text #17

Max Range: 1.7436. Min Range: -1.7436

Max Act: 1.2377. Min Act: -0.0001

Data Index: 266885 (C4 (Web Text))

Max Activating Token Index: 364

Text #18

Max Range: 1.7436. Min Range: -1.7436

Max Act: 1.0961. Min Act: -0.0001

Data Index: 859325 (C4 (Web Text))

Max Activating Token Index: 633

Text #19

Max Range: 1.7436. Min Range: -1.7436

Max Act: 1.1582. Min Act: -0.0001

Data Index: 964522 (C4 (Web Text))

Max Activating Token Index: 442