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

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

Neuron 5897 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2475. Min Range: -0.2475

Max Act: 0.2475. Min Act: -0.0002

Data Index: 1110302 (C4 (Web Text))

Max Activating Token Index: 38

Text #1

Max Range: 0.2475. Min Range: -0.2475

Max Act: 0.2391. Min Act: -0.0002

Data Index: 184197 (C4 (Web Text))

Max Activating Token Index: 613

Text #2

Max Range: 0.2475. Min Range: -0.2475

Max Act: 0.2012. Min Act: -0.0002

Data Index: 587946 (C4 (Web Text))

Max Activating Token Index: 636

Text #3

Max Range: 0.2475. Min Range: -0.2475

Max Act: 0.1911. Min Act: -0.0002

Data Index: 61015 (C4 (Web Text))

Max Activating Token Index: 573

Text #4

Max Range: 0.2475. Min Range: -0.2475

Max Act: 0.1865. Min Act: -0.0002

Data Index: 1267217 (C4 (Web Text))

Max Activating Token Index: 95

Text #5

Max Range: 0.2475. Min Range: -0.2475

Max Act: 0.1806. Min Act: -0.0002

Data Index: 183620 (C4 (Web Text))

Max Activating Token Index: 359

Text #6

Max Range: 0.2475. Min Range: -0.2475

Max Act: 0.1729. Min Act: -0.0002

Data Index: 678112 (C4 (Web Text))

Max Activating Token Index: 826

Text #7

Max Range: 0.2475. Min Range: -0.2475

Max Act: 0.1655. Min Act: -0.0002

Data Index: 457595 (C4 (Web Text))

Max Activating Token Index: 101

Text #8

Max Range: 0.2475. Min Range: -0.2475

Max Act: 0.1706. Min Act: -0.0002

Data Index: 1255385 (C4 (Web Text))

Max Activating Token Index: 650

Text #9

Max Range: 0.2475. Min Range: -0.2475

Max Act: 0.1648. Min Act: -0.0002

Data Index: 480657 (C4 (Web Text))

Max Activating Token Index: 712

Text #10

Max Range: 0.2475. Min Range: -0.2475

Max Act: 0.1535. Min Act: -0.0002

Data Index: 118960 (C4 (Web Text))

Max Activating Token Index: 112

Text #11

Max Range: 0.2475. Min Range: -0.2475

Max Act: 0.1524. Min Act: -0.0001

Data Index: 598312 (C4 (Web Text))

Max Activating Token Index: 335

Text #12

Max Range: 0.2475. Min Range: -0.2475

Max Act: 0.1580. Min Act: -0.0002

Data Index: 1010347 (C4 (Web Text))

Max Activating Token Index: 489

Text #13

Max Range: 0.2475. Min Range: -0.2475

Max Act: 0.1569. Min Act: -0.0002

Data Index: 847775 (C4 (Web Text))

Max Activating Token Index: 606

Text #14

Max Range: 0.2475. Min Range: -0.2475

Max Act: 0.1560. Min Act: -0.0002

Data Index: 628337 (C4 (Web Text))

Max Activating Token Index: 185

Text #15

Max Range: 0.2475. Min Range: -0.2475

Max Act: 0.1530. Min Act: -0.0002

Data Index: 224248 (C4 (Web Text))

Max Activating Token Index: 713

Text #16

Max Range: 0.2475. Min Range: -0.2475

Max Act: 0.1479. Min Act: -0.0002

Data Index: 526249 (C4 (Web Text))

Max Activating Token Index: 236

Text #17

Max Range: 0.2475. Min Range: -0.2475

Max Act: 0.1443. Min Act: -0.0002

Data Index: 1084249 (C4 (Web Text))

Max Activating Token Index: 274

Text #18

Max Range: 0.2475. Min Range: -0.2475

Max Act: 0.1436. Min Act: -0.0002

Data Index: 951834 (C4 (Web Text))

Max Activating Token Index: 121

Text #19

Max Range: 0.2475. Min Range: -0.2475

Max Act: 0.1375. Min Act: -0.0002

Data Index: 704788 (C4 (Web Text))

Max Activating Token Index: 895