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

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

Neuron 4050 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: 1.5646. Min Range: -1.5646

Max Act: 1.5646. Min Act: -0.0000

Data Index: 28440 (C4 (Web Text))

Max Activating Token Index: 656

Text #1

Max Range: 1.5646. Min Range: -1.5646

Max Act: 1.5389. Min Act: -0.0000

Data Index: 95871 (C4 (Web Text))

Max Activating Token Index: 755

Text #2

Max Range: 1.5646. Min Range: -1.5646

Max Act: 1.3987. Min Act: -0.0000

Data Index: 621803 (C4 (Web Text))

Max Activating Token Index: 652

Text #3

Max Range: 1.5646. Min Range: -1.5646

Max Act: 1.4506. Min Act: -0.0000

Data Index: 741781 (C4 (Web Text))

Max Activating Token Index: 594

Text #4

Max Range: 1.5646. Min Range: -1.5646

Max Act: 1.3909. Min Act: -0.0000

Data Index: 705997 (C4 (Web Text))

Max Activating Token Index: 237

Text #5

Max Range: 1.5646. Min Range: -1.5646

Max Act: 1.3606. Min Act: -0.0000

Data Index: 861838 (C4 (Web Text))

Max Activating Token Index: 154

Text #6

Max Range: 1.5646. Min Range: -1.5646

Max Act: 1.3326. Min Act: -0.0000

Data Index: 96793 (C4 (Web Text))

Max Activating Token Index: 475

Text #7

Max Range: 1.5646. Min Range: -1.5646

Max Act: 1.3644. Min Act: -0.0000

Data Index: 401797 (C4 (Web Text))

Max Activating Token Index: 631

Text #8

Max Range: 1.5646. Min Range: -1.5646

Max Act: 1.4353. Min Act: -0.0000

Data Index: 580437 (C4 (Web Text))

Max Activating Token Index: 202

Text #9

Max Range: 1.5646. Min Range: -1.5646

Max Act: 1.3444. Min Act: -0.0000

Data Index: 1041049 (C4 (Web Text))

Max Activating Token Index: 613

Text #10

Max Range: 1.5646. Min Range: -1.5646

Max Act: 1.3364. Min Act: -0.0000

Data Index: 1219909 (C4 (Web Text))

Max Activating Token Index: 799

Text #11

Max Range: 1.5646. Min Range: -1.5646

Max Act: 1.1544. Min Act: -0.0000

Data Index: 635507 (C4 (Web Text))

Max Activating Token Index: 751

Text #12

Max Range: 1.5646. Min Range: -1.5646

Max Act: 1.1520. Min Act: -0.0000

Data Index: 221146 (C4 (Web Text))

Max Activating Token Index: 32

Text #13

Max Range: 1.5646. Min Range: -1.5646

Max Act: 1.0967. Min Act: -0.0000

Data Index: 178353 (C4 (Web Text))

Max Activating Token Index: 217

Text #14

Max Range: 1.5646. Min Range: -1.5646

Max Act: 1.1467. Min Act: -0.0000

Data Index: 1262109 (C4 (Web Text))

Max Activating Token Index: 611

Text #15

Max Range: 1.5646. Min Range: -1.5646

Max Act: 1.1014. Min Act: -0.0000

Data Index: 815370 (C4 (Web Text))

Max Activating Token Index: 860

Text #16

Max Range: 1.5646. Min Range: -1.5646

Max Act: 0.9878. Min Act: -0.0000

Data Index: 139089 (C4 (Web Text))

Max Activating Token Index: 962

Text #17

Max Range: 1.5646. Min Range: -1.5646

Max Act: 1.0362. Min Act: -0.0000

Data Index: 1189183 (C4 (Web Text))

Max Activating Token Index: 254

Text #18

Max Range: 1.5646. Min Range: -1.5646

Max Act: 0.9792. Min Act: -0.0000

Data Index: 1274449 (C4 (Web Text))

Max Activating Token Index: 391

Text #19

Max Range: 1.5646. Min Range: -1.5646

Max Act: 0.8818. Min Act: -0.0000

Data Index: 347058 (C4 (Web Text))

Max Activating Token Index: 378