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

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

Neuron 652 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: 1.9286. Min Range: -1.9286

Max Act: 1.9286. Min Act: -0.0001

Data Index: 449087 (C4 (Web Text))

Max Activating Token Index: 1013

Text #1

Max Range: 1.9286. Min Range: -1.9286

Max Act: 1.5792. Min Act: -0.0001

Data Index: 519363 (C4 (Web Text))

Max Activating Token Index: 893

Text #2

Max Range: 1.9286. Min Range: -1.9286

Max Act: 1.3986. Min Act: -0.0001

Data Index: 1004125 (C4 (Web Text))

Max Activating Token Index: 697

Text #3

Max Range: 1.9286. Min Range: -1.9286

Max Act: 1.4173. Min Act: -0.0001

Data Index: 321899 (C4 (Web Text))

Max Activating Token Index: 389

Text #4

Max Range: 1.9286. Min Range: -1.9286

Max Act: 1.3053. Min Act: -0.0001

Data Index: 262594 (C4 (Web Text))

Max Activating Token Index: 479

Text #5

Max Range: 1.9286. Min Range: -1.9286

Max Act: 1.4173. Min Act: -0.0001

Data Index: 53946 (C4 (Web Text))

Max Activating Token Index: 767

Text #6

Max Range: 1.9286. Min Range: -1.9286

Max Act: 1.2128. Min Act: -0.0001

Data Index: 1291574 (C4 (Web Text))

Max Activating Token Index: 509

Text #7

Max Range: 1.9286. Min Range: -1.9286

Max Act: 1.1489. Min Act: -0.0001

Data Index: 72229 (C4 (Web Text))

Max Activating Token Index: 678

Text #8

Max Range: 1.9286. Min Range: -1.9286

Max Act: 1.3188. Min Act: -0.0001

Data Index: 918832 (C4 (Web Text))

Max Activating Token Index: 20

Text #9

Max Range: 1.9286. Min Range: -1.9286

Max Act: 1.2583. Min Act: -0.0001

Data Index: 129240 (C4 (Web Text))

Max Activating Token Index: 397

Text #10

Max Range: 1.9286. Min Range: -1.9286

Max Act: 1.1439. Min Act: -0.0001

Data Index: 1047156 (C4 (Web Text))

Max Activating Token Index: 266

Text #11

Max Range: 1.9286. Min Range: -1.9286

Max Act: 1.2411. Min Act: -0.0001

Data Index: 167140 (C4 (Web Text))

Max Activating Token Index: 303

Text #12

Max Range: 1.9286. Min Range: -1.9286

Max Act: 1.1850. Min Act: -0.0001

Data Index: 968368 (C4 (Web Text))

Max Activating Token Index: 962

Text #13

Max Range: 1.9286. Min Range: -1.9286

Max Act: 1.0906. Min Act: -0.0001

Data Index: 1030099 (C4 (Web Text))

Max Activating Token Index: 753

Text #14

Max Range: 1.9286. Min Range: -1.9286

Max Act: 1.1468. Min Act: -0.0001

Data Index: 352011 (C4 (Web Text))

Max Activating Token Index: 430

Text #15

Max Range: 1.9286. Min Range: -1.9286

Max Act: 1.1793. Min Act: -0.0001

Data Index: 26128 (C4 (Web Text))

Max Activating Token Index: 432

Text #16

Max Range: 1.9286. Min Range: -1.9286

Max Act: 1.1126. Min Act: -0.0001

Data Index: 726329 (C4 (Web Text))

Max Activating Token Index: 921

Text #17

Max Range: 1.9286. Min Range: -1.9286

Max Act: 1.1297. Min Act: -0.0001

Data Index: 1109201 (C4 (Web Text))

Max Activating Token Index: 875

Text #18

Max Range: 1.9286. Min Range: -1.9286

Max Act: 1.1301. Min Act: -0.0001

Data Index: 807524 (C4 (Web Text))

Max Activating Token Index: 46

Text #19

Max Range: 1.9286. Min Range: -1.9286

Max Act: 1.1659. Min Act: -0.0001

Data Index: 97918 (C4 (Web Text))

Max Activating Token Index: 641