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

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

Neuron 2297 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: 0.0578. Min Range: -0.0578

Max Act: 0.0542. Min Act: -0.0001

Data Index: 366307 (C4 (Web Text))

Max Activating Token Index: 892

Text #1

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0575. Min Act: -0.0001

Data Index: 707269 (C4 (Web Text))

Max Activating Token Index: 137

Text #2

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0578. Min Act: -0.0001

Data Index: 587706 (C4 (Web Text))

Max Activating Token Index: 458

Text #3

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0508. Min Act: -0.0001

Data Index: 538950 (C4 (Web Text))

Max Activating Token Index: 543

Text #4

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0470. Min Act: -0.0001

Data Index: 805831 (C4 (Web Text))

Max Activating Token Index: 606

Text #5

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0508. Min Act: -0.0001

Data Index: 1099162 (C4 (Web Text))

Max Activating Token Index: 563

Text #6

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0493. Min Act: -0.0001

Data Index: 295815 (C4 (Web Text))

Max Activating Token Index: 426

Text #7

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0500. Min Act: -0.0001

Data Index: 1489820 (Python Code)

Max Activating Token Index: 106

Text #8

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0519. Min Act: -0.0001

Data Index: 1614910 (Python Code)

Max Activating Token Index: 870

Text #9

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0430. Min Act: -0.0001

Data Index: 690823 (C4 (Web Text))

Max Activating Token Index: 819

Text #10

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0452. Min Act: -0.0001

Data Index: 1526356 (Python Code)

Max Activating Token Index: 627

Text #11

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0421. Min Act: -0.0001

Data Index: 908161 (C4 (Web Text))

Max Activating Token Index: 534

Text #12

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0428. Min Act: -0.0001

Data Index: 401199 (C4 (Web Text))

Max Activating Token Index: 488

Text #13

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0488. Min Act: -0.0001

Data Index: 738438 (C4 (Web Text))

Max Activating Token Index: 596

Text #14

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0445. Min Act: -0.0001

Data Index: 1582456 (Python Code)

Max Activating Token Index: 999

Text #15

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0448. Min Act: -0.0001

Data Index: 965831 (C4 (Web Text))

Max Activating Token Index: 512

Text #16

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0438. Min Act: -0.0001

Data Index: 1510964 (Python Code)

Max Activating Token Index: 666

Text #17

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0444. Min Act: -0.0001

Data Index: 1418242 (Python Code)

Max Activating Token Index: 883

Text #18

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0407. Min Act: -0.0001

Data Index: 1208678 (C4 (Web Text))

Max Activating Token Index: 247

Text #19

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0409. Min Act: -0.0001

Data Index: 1415275 (Python Code)

Max Activating Token Index: 1016