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

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

Neuron 5043 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.1724. Min Range: -2.1724

Max Act: 2.1724. Min Act: -0.0000

Data Index: 1354115 (C4 (Web Text))

Max Activating Token Index: 585

Text #1

Max Range: 2.1724. Min Range: -2.1724

Max Act: 2.1285. Min Act: -0.0000

Data Index: 168332 (C4 (Web Text))

Max Activating Token Index: 68

Text #2

Max Range: 2.1724. Min Range: -2.1724

Max Act: 2.1346. Min Act: -0.0000

Data Index: 450229 (C4 (Web Text))

Max Activating Token Index: 126

Text #3

Max Range: 2.1724. Min Range: -2.1724

Max Act: 2.0763. Min Act: -0.0000

Data Index: 713096 (C4 (Web Text))

Max Activating Token Index: 1005

Text #4

Max Range: 2.1724. Min Range: -2.1724

Max Act: 2.0481. Min Act: -0.0000

Data Index: 1299218 (C4 (Web Text))

Max Activating Token Index: 648

Text #5

Max Range: 2.1724. Min Range: -2.1724

Max Act: 1.9946. Min Act: -0.0000

Data Index: 1184762 (C4 (Web Text))

Max Activating Token Index: 168

Text #6

Max Range: 2.1724. Min Range: -2.1724

Max Act: 1.7995. Min Act: -0.0000

Data Index: 1125473 (C4 (Web Text))

Max Activating Token Index: 748

Text #7

Max Range: 2.1724. Min Range: -2.1724

Max Act: 1.8967. Min Act: -0.0000

Data Index: 754028 (C4 (Web Text))

Max Activating Token Index: 880

Text #8

Max Range: 2.1724. Min Range: -2.1724

Max Act: 1.7920. Min Act: -0.0000

Data Index: 934198 (C4 (Web Text))

Max Activating Token Index: 841

Text #9

Max Range: 2.1724. Min Range: -2.1724

Max Act: 1.8402. Min Act: -0.0000

Data Index: 341700 (C4 (Web Text))

Max Activating Token Index: 947

Text #10

Max Range: 2.1724. Min Range: -2.1724

Max Act: 1.9319. Min Act: -0.0000

Data Index: 1003243 (C4 (Web Text))

Max Activating Token Index: 667

Text #11

Max Range: 2.1724. Min Range: -2.1724

Max Act: 1.6254. Min Act: -0.0000

Data Index: 761101 (C4 (Web Text))

Max Activating Token Index: 778

Text #12

Max Range: 2.1724. Min Range: -2.1724

Max Act: 1.8747. Min Act: -0.0000

Data Index: 659226 (C4 (Web Text))

Max Activating Token Index: 215

Text #13

Max Range: 2.1724. Min Range: -2.1724

Max Act: 1.6658. Min Act: -0.0000

Data Index: 1042251 (C4 (Web Text))

Max Activating Token Index: 566

Text #14

Max Range: 2.1724. Min Range: -2.1724

Max Act: 1.7588. Min Act: -0.0000

Data Index: 677297 (C4 (Web Text))

Max Activating Token Index: 682

Text #15

Max Range: 2.1724. Min Range: -2.1724

Max Act: 1.7434. Min Act: -0.0000

Data Index: 82325 (C4 (Web Text))

Max Activating Token Index: 953

Text #16

Max Range: 2.1724. Min Range: -2.1724

Max Act: 1.7388. Min Act: -0.0000

Data Index: 419056 (C4 (Web Text))

Max Activating Token Index: 814

Text #17

Max Range: 2.1724. Min Range: -2.1724

Max Act: 1.7237. Min Act: -0.0000

Data Index: 623441 (C4 (Web Text))

Max Activating Token Index: 736

Text #18

Max Range: 2.1724. Min Range: -2.1724

Max Act: 2.0172. Min Act: -0.0000

Data Index: 1126472 (C4 (Web Text))

Max Activating Token Index: 815

Text #19

Max Range: 2.1724. Min Range: -2.1724

Max Act: 1.7046. Min Act: -0.0000

Data Index: 680434 (C4 (Web Text))

Max Activating Token Index: 528