Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3573 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 4.3402. Min Range: -4.3402

Max Act: 4.3402. Min Act: -0.0000

Data Index: 1614075 (Python Code)

Max Activating Token Index: 924

Text #1

Max Range: 4.3402. Min Range: -4.3402

Max Act: 4.3022. Min Act: -0.0000

Data Index: 1506518 (Python Code)

Max Activating Token Index: 874

Text #2

Max Range: 4.3402. Min Range: -4.3402

Max Act: 4.1740. Min Act: -0.0000

Data Index: 1494693 (Python Code)

Max Activating Token Index: 665

Text #3

Max Range: 4.3402. Min Range: -4.3402

Max Act: 4.0848. Min Act: -0.0000

Data Index: 1381414 (Python Code)

Max Activating Token Index: 811

Text #4

Max Range: 4.3402. Min Range: -4.3402

Max Act: 3.8631. Min Act: -0.0000

Data Index: 1555375 (Python Code)

Max Activating Token Index: 403

Text #5

Max Range: 4.3402. Min Range: -4.3402

Max Act: 3.9407. Min Act: -0.0000

Data Index: 1606638 (Python Code)

Max Activating Token Index: 535

Text #6

Max Range: 4.3402. Min Range: -4.3402

Max Act: 3.9087. Min Act: -0.0000

Data Index: 1379346 (Python Code)

Max Activating Token Index: 981

Text #7

Max Range: 4.3402. Min Range: -4.3402

Max Act: 3.8456. Min Act: -0.0000

Data Index: 1457983 (Python Code)

Max Activating Token Index: 479

Text #8

Max Range: 4.3402. Min Range: -4.3402

Max Act: 3.9054. Min Act: -0.0000

Data Index: 1633606 (Python Code)

Max Activating Token Index: 346

Text #9

Max Range: 4.3402. Min Range: -4.3402

Max Act: 3.6545. Min Act: -0.0000

Data Index: 1380300 (Python Code)

Max Activating Token Index: 437

Text #10

Max Range: 4.3402. Min Range: -4.3402

Max Act: 3.5643. Min Act: -0.0000

Data Index: 1415214 (Python Code)

Max Activating Token Index: 890

Text #11

Max Range: 4.3402. Min Range: -4.3402

Max Act: 3.6547. Min Act: -0.0000

Data Index: 1504061 (Python Code)

Max Activating Token Index: 763

Text #12

Max Range: 4.3402. Min Range: -4.3402

Max Act: 3.1462. Min Act: -0.0000

Data Index: 1461347 (Python Code)

Max Activating Token Index: 701

Text #13

Max Range: 4.3402. Min Range: -4.3402

Max Act: 3.4148. Min Act: -0.0000

Data Index: 1599800 (Python Code)

Max Activating Token Index: 528

Text #14

Max Range: 4.3402. Min Range: -4.3402

Max Act: 3.2094. Min Act: -0.0000

Data Index: 1509822 (Python Code)

Max Activating Token Index: 885

Text #15

Max Range: 4.3402. Min Range: -4.3402

Max Act: 3.2790. Min Act: -0.0000

Data Index: 1647408 (Python Code)

Max Activating Token Index: 578

Text #16

Max Range: 4.3402. Min Range: -4.3402

Max Act: 3.2417. Min Act: -0.0000

Data Index: 1615485 (Python Code)

Max Activating Token Index: 1013

Text #17

Max Range: 4.3402. Min Range: -4.3402

Max Act: 3.2155. Min Act: -0.0000

Data Index: 20370 (C4 (Web Text))

Max Activating Token Index: 359

Text #18

Max Range: 4.3402. Min Range: -4.3402

Max Act: 3.2444. Min Act: -0.0000

Data Index: 1516696 (Python Code)

Max Activating Token Index: 614

Text #19

Max Range: 4.3402. Min Range: -4.3402

Max Act: 3.2459. Min Act: -0.0000

Data Index: 439921 (C4 (Web Text))

Max Activating Token Index: 76