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

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

Neuron 847 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1309. Min Range: -2.1309

Max Act: 2.1309. Min Act: -0.0000

Data Index: 1470826 (Python Code)

Max Activating Token Index: 846

Text #1

Max Range: 2.1309. Min Range: -2.1309

Max Act: 2.0264. Min Act: -0.0000

Data Index: 1626267 (Python Code)

Max Activating Token Index: 583

Text #2

Max Range: 2.1309. Min Range: -2.1309

Max Act: 2.1152. Min Act: -0.0000

Data Index: 1567563 (Python Code)

Max Activating Token Index: 450

Text #3

Max Range: 2.1309. Min Range: -2.1309

Max Act: 1.9601. Min Act: -0.0000

Data Index: 1515826 (Python Code)

Max Activating Token Index: 300

Text #4

Max Range: 2.1309. Min Range: -2.1309

Max Act: 1.9096. Min Act: -0.0000

Data Index: 1525718 (Python Code)

Max Activating Token Index: 345

Text #5

Max Range: 2.1309. Min Range: -2.1309

Max Act: 1.6920. Min Act: -0.0000

Data Index: 1617356 (Python Code)

Max Activating Token Index: 463

Text #6

Max Range: 2.1309. Min Range: -2.1309

Max Act: 1.7258. Min Act: -0.0000

Data Index: 1407000 (Python Code)

Max Activating Token Index: 645

Text #7

Max Range: 2.1309. Min Range: -2.1309

Max Act: 1.7705. Min Act: -0.0000

Data Index: 1521019 (Python Code)

Max Activating Token Index: 862

Text #8

Max Range: 2.1309. Min Range: -2.1309

Max Act: 1.7438. Min Act: -0.0000

Data Index: 1544125 (Python Code)

Max Activating Token Index: 357

Text #9

Max Range: 2.1309. Min Range: -2.1309

Max Act: 1.6789. Min Act: -0.0000

Data Index: 1459544 (Python Code)

Max Activating Token Index: 270

Text #10

Max Range: 2.1309. Min Range: -2.1309

Max Act: 1.6064. Min Act: -0.0000

Data Index: 1622625 (Python Code)

Max Activating Token Index: 905

Text #11

Max Range: 2.1309. Min Range: -2.1309

Max Act: 1.6314. Min Act: -0.0000

Data Index: 1537735 (Python Code)

Max Activating Token Index: 970

Text #12

Max Range: 2.1309. Min Range: -2.1309

Max Act: 1.6638. Min Act: -0.0000

Data Index: 1622451 (Python Code)

Max Activating Token Index: 748

Text #13

Max Range: 2.1309. Min Range: -2.1309

Max Act: 1.6628. Min Act: -0.0000

Data Index: 1526512 (Python Code)

Max Activating Token Index: 870

Text #14

Max Range: 2.1309. Min Range: -2.1309

Max Act: 1.6508. Min Act: -0.0000

Data Index: 1485292 (Python Code)

Max Activating Token Index: 367

Text #15

Max Range: 2.1309. Min Range: -2.1309

Max Act: 1.6158. Min Act: -0.0000

Data Index: 1569969 (Python Code)

Max Activating Token Index: 915

Text #16

Max Range: 2.1309. Min Range: -2.1309

Max Act: 1.6153. Min Act: -0.0000

Data Index: 303470 (C4 (Web Text))

Max Activating Token Index: 657

Text #17

Max Range: 2.1309. Min Range: -2.1309

Max Act: 1.6642. Min Act: -0.0000

Data Index: 1650030 (Python Code)

Max Activating Token Index: 675

Text #18

Max Range: 2.1309. Min Range: -2.1309

Max Act: 1.6503. Min Act: -0.0000

Data Index: 1547074 (Python Code)

Max Activating Token Index: 883

Text #19

Max Range: 2.1309. Min Range: -2.1309

Max Act: 1.5186. Min Act: -0.0000

Data Index: 370701 (C4 (Web Text))

Max Activating Token Index: 419