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

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

Neuron 4387 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0646. Min Range: -0.0646

Max Act: 0.0646. Min Act: -0.0000

Data Index: 196594 (C4 (Web Text))

Max Activating Token Index: 757

Text #1

Max Range: 0.0646. Min Range: -0.0646

Max Act: 0.0554. Min Act: -0.0000

Data Index: 1328216 (C4 (Web Text))

Max Activating Token Index: 568

Text #2

Max Range: 0.0646. Min Range: -0.0646

Max Act: 0.0444. Min Act: -0.0001

Data Index: 637496 (C4 (Web Text))

Max Activating Token Index: 586

Text #3

Max Range: 0.0646. Min Range: -0.0646

Max Act: 0.0431. Min Act: -0.0000

Data Index: 548273 (C4 (Web Text))

Max Activating Token Index: 665

Text #4

Max Range: 0.0646. Min Range: -0.0646

Max Act: 0.0482. Min Act: -0.0001

Data Index: 1241875 (C4 (Web Text))

Max Activating Token Index: 559

Text #5

Max Range: 0.0646. Min Range: -0.0646

Max Act: 0.0439. Min Act: -0.0000

Data Index: 237000 (C4 (Web Text))

Max Activating Token Index: 621

Text #6

Max Range: 0.0646. Min Range: -0.0646

Max Act: 0.0448. Min Act: -0.0001

Data Index: 885259 (C4 (Web Text))

Max Activating Token Index: 340

Text #7

Max Range: 0.0646. Min Range: -0.0646

Max Act: 0.0466. Min Act: -0.0000

Data Index: 60235 (C4 (Web Text))

Max Activating Token Index: 120

Text #8

Max Range: 0.0646. Min Range: -0.0646

Max Act: 0.0449. Min Act: -0.0001

Data Index: 656118 (C4 (Web Text))

Max Activating Token Index: 902

Text #9

Max Range: 0.0646. Min Range: -0.0646

Max Act: 0.0382. Min Act: -0.0001

Data Index: 1231147 (C4 (Web Text))

Max Activating Token Index: 695

Text #10

Max Range: 0.0646. Min Range: -0.0646

Max Act: 0.0412. Min Act: -0.0000

Data Index: 123796 (C4 (Web Text))

Max Activating Token Index: 72

Text #11

Max Range: 0.0646. Min Range: -0.0646

Max Act: 0.0347. Min Act: -0.0000

Data Index: 931480 (C4 (Web Text))

Max Activating Token Index: 269

Text #12

Max Range: 0.0646. Min Range: -0.0646

Max Act: 0.0428. Min Act: -0.0000

Data Index: 76240 (C4 (Web Text))

Max Activating Token Index: 501

Text #13

Max Range: 0.0646. Min Range: -0.0646

Max Act: 0.0415. Min Act: -0.0000

Data Index: 725119 (C4 (Web Text))

Max Activating Token Index: 94

Text #14

Max Range: 0.0646. Min Range: -0.0646

Max Act: 0.0399. Min Act: -0.0000

Data Index: 1259453 (C4 (Web Text))

Max Activating Token Index: 883

Text #15

Max Range: 0.0646. Min Range: -0.0646

Max Act: 0.0370. Min Act: -0.0000

Data Index: 1054107 (C4 (Web Text))

Max Activating Token Index: 645

Text #16

Max Range: 0.0646. Min Range: -0.0646

Max Act: 0.0387. Min Act: -0.0000

Data Index: 606240 (C4 (Web Text))

Max Activating Token Index: 908

Text #17

Max Range: 0.0646. Min Range: -0.0646

Max Act: 0.0390. Min Act: -0.0001

Data Index: 464139 (C4 (Web Text))

Max Activating Token Index: 552

Text #18

Max Range: 0.0646. Min Range: -0.0646

Max Act: 0.0401. Min Act: -0.0000

Data Index: 200639 (C4 (Web Text))

Max Activating Token Index: 615

Text #19

Max Range: 0.0646. Min Range: -0.0646

Max Act: 0.0405. Min Act: -0.0000

Data Index: 733559 (C4 (Web Text))

Max Activating Token Index: 444