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

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

Neuron 1493 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4301. Min Range: -0.4301

Max Act: 0.4301. Min Act: -0.0000

Data Index: 1478474 (Python Code)

Max Activating Token Index: 69

Text #1

Max Range: 0.4301. Min Range: -0.4301

Max Act: 0.3963. Min Act: -0.0000

Data Index: 1546572 (Python Code)

Max Activating Token Index: 551

Text #2

Max Range: 0.4301. Min Range: -0.4301

Max Act: 0.3781. Min Act: -0.0000

Data Index: 1518101 (Python Code)

Max Activating Token Index: 481

Text #3

Max Range: 0.4301. Min Range: -0.4301

Max Act: 0.3874. Min Act: -0.0000

Data Index: 1595603 (Python Code)

Max Activating Token Index: 594

Text #4

Max Range: 0.4301. Min Range: -0.4301

Max Act: 0.3329. Min Act: -0.0000

Data Index: 1525951 (Python Code)

Max Activating Token Index: 281

Text #5

Max Range: 0.4301. Min Range: -0.4301

Max Act: 0.3115. Min Act: -0.0000

Data Index: 1631154 (Python Code)

Max Activating Token Index: 649

Text #6

Max Range: 0.4301. Min Range: -0.4301

Max Act: 0.3007. Min Act: -0.0000

Data Index: 1475828 (Python Code)

Max Activating Token Index: 212

Text #7

Max Range: 0.4301. Min Range: -0.4301

Max Act: 0.2899. Min Act: -0.0000

Data Index: 1654558 (Python Code)

Max Activating Token Index: 306

Text #8

Max Range: 0.4301. Min Range: -0.4301

Max Act: 0.2863. Min Act: -0.0000

Data Index: 1401261 (Python Code)

Max Activating Token Index: 815

Text #9

Max Range: 0.4301. Min Range: -0.4301

Max Act: 0.2809. Min Act: -0.0000

Data Index: 1421649 (Python Code)

Max Activating Token Index: 931

Text #10

Max Range: 0.4301. Min Range: -0.4301

Max Act: 0.2754. Min Act: -0.0000

Data Index: 242 (C4 (Web Text))

Max Activating Token Index: 913

Text #11

Max Range: 0.4301. Min Range: -0.4301

Max Act: 0.2999. Min Act: -0.0000

Data Index: 1578917 (Python Code)

Max Activating Token Index: 576

Text #12

Max Range: 0.4301. Min Range: -0.4301

Max Act: 0.2884. Min Act: -0.0000

Data Index: 1654349 (Python Code)

Max Activating Token Index: 604

Text #13

Max Range: 0.4301. Min Range: -0.4301

Max Act: 0.2866. Min Act: -0.0000

Data Index: 494636 (C4 (Web Text))

Max Activating Token Index: 192

Text #14

Max Range: 0.4301. Min Range: -0.4301

Max Act: 0.2740. Min Act: -0.0000

Data Index: 1429071 (Python Code)

Max Activating Token Index: 82

Text #15

Max Range: 0.4301. Min Range: -0.4301

Max Act: 0.2702. Min Act: -0.0000

Data Index: 1636866 (Python Code)

Max Activating Token Index: 261

Text #16

Max Range: 0.4301. Min Range: -0.4301

Max Act: 0.2632. Min Act: -0.0000

Data Index: 1480977 (Python Code)

Max Activating Token Index: 295

Text #17

Max Range: 0.4301. Min Range: -0.4301

Max Act: 0.2564. Min Act: -0.0000

Data Index: 1630132 (Python Code)

Max Activating Token Index: 768

Text #18

Max Range: 0.4301. Min Range: -0.4301

Max Act: 0.2580. Min Act: -0.0000

Data Index: 1385511 (Python Code)

Max Activating Token Index: 14

Text #19

Max Range: 0.4301. Min Range: -0.4301

Max Act: 0.2528. Min Act: -0.0000

Data Index: 1321222 (C4 (Web Text))

Max Activating Token Index: 371