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

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

Neuron 5416 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1282. Min Range: -2.1282

Max Act: 2.1282. Min Act: -0.0000

Data Index: 1365103 (Python Code)

Max Activating Token Index: 74

Text #1

Max Range: 2.1282. Min Range: -2.1282

Max Act: 2.0547. Min Act: -0.0000

Data Index: 428222 (C4 (Web Text))

Max Activating Token Index: 982

Text #2

Max Range: 2.1282. Min Range: -2.1282

Max Act: 1.9890. Min Act: -0.0000

Data Index: 89366 (C4 (Web Text))

Max Activating Token Index: 862

Text #3

Max Range: 2.1282. Min Range: -2.1282

Max Act: 1.9518. Min Act: -0.0000

Data Index: 747298 (C4 (Web Text))

Max Activating Token Index: 376

Text #4

Max Range: 2.1282. Min Range: -2.1282

Max Act: 1.9687. Min Act: -0.0000

Data Index: 1003166 (C4 (Web Text))

Max Activating Token Index: 1000

Text #5

Max Range: 2.1282. Min Range: -2.1282

Max Act: 1.7687. Min Act: -0.0000

Data Index: 1081063 (C4 (Web Text))

Max Activating Token Index: 518

Text #6

Max Range: 2.1282. Min Range: -2.1282

Max Act: 1.8387. Min Act: -0.0000

Data Index: 1103119 (C4 (Web Text))

Max Activating Token Index: 670

Text #7

Max Range: 2.1282. Min Range: -2.1282

Max Act: 1.8140. Min Act: -0.0000

Data Index: 691003 (C4 (Web Text))

Max Activating Token Index: 373

Text #8

Max Range: 2.1282. Min Range: -2.1282

Max Act: 1.9077. Min Act: -0.0000

Data Index: 1007290 (C4 (Web Text))

Max Activating Token Index: 706

Text #9

Max Range: 2.1282. Min Range: -2.1282

Max Act: 1.7338. Min Act: -0.0000

Data Index: 716174 (C4 (Web Text))

Max Activating Token Index: 889

Text #10

Max Range: 2.1282. Min Range: -2.1282

Max Act: 1.5921. Min Act: -0.0000

Data Index: 603650 (C4 (Web Text))

Max Activating Token Index: 905

Text #11

Max Range: 2.1282. Min Range: -2.1282

Max Act: 1.6937. Min Act: -0.0000

Data Index: 1295846 (C4 (Web Text))

Max Activating Token Index: 209

Text #12

Max Range: 2.1282. Min Range: -2.1282

Max Act: 1.6899. Min Act: -0.0000

Data Index: 1111374 (C4 (Web Text))

Max Activating Token Index: 34

Text #13

Max Range: 2.1282. Min Range: -2.1282

Max Act: 1.6790. Min Act: -0.0000

Data Index: 698054 (C4 (Web Text))

Max Activating Token Index: 54

Text #14

Max Range: 2.1282. Min Range: -2.1282

Max Act: 1.7588. Min Act: -0.0000

Data Index: 518534 (C4 (Web Text))

Max Activating Token Index: 898

Text #15

Max Range: 2.1282. Min Range: -2.1282

Max Act: 1.6875. Min Act: -0.0000

Data Index: 563011 (C4 (Web Text))

Max Activating Token Index: 774

Text #16

Max Range: 2.1282. Min Range: -2.1282

Max Act: 1.6333. Min Act: -0.0000

Data Index: 349063 (C4 (Web Text))

Max Activating Token Index: 583

Text #17

Max Range: 2.1282. Min Range: -2.1282

Max Act: 1.6099. Min Act: -0.0000

Data Index: 1140385 (C4 (Web Text))

Max Activating Token Index: 821

Text #18

Max Range: 2.1282. Min Range: -2.1282

Max Act: 1.6165. Min Act: -0.0000

Data Index: 1442939 (Python Code)

Max Activating Token Index: 642

Text #19

Max Range: 2.1282. Min Range: -2.1282

Max Act: 1.5956. Min Act: -0.0000

Data Index: 737678 (C4 (Web Text))

Max Activating Token Index: 121