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

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

Neuron 4687 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5140. Min Range: -0.5140

Max Act: 0.5140. Min Act: -0.0000

Data Index: 737371 (C4 (Web Text))

Max Activating Token Index: 1006

Text #1

Max Range: 0.5140. Min Range: -0.5140

Max Act: 0.4102. Min Act: -0.0000

Data Index: 449487 (C4 (Web Text))

Max Activating Token Index: 347

Text #2

Max Range: 0.5140. Min Range: -0.5140

Max Act: 0.4501. Min Act: -0.0001

Data Index: 46780 (C4 (Web Text))

Max Activating Token Index: 363

Text #3

Max Range: 0.5140. Min Range: -0.5140

Max Act: 0.3974. Min Act: -0.0000

Data Index: 88422 (C4 (Web Text))

Max Activating Token Index: 952

Text #4

Max Range: 0.5140. Min Range: -0.5140

Max Act: 0.3919. Min Act: -0.0000

Data Index: 891889 (C4 (Web Text))

Max Activating Token Index: 781

Text #5

Max Range: 0.5140. Min Range: -0.5140

Max Act: 0.3876. Min Act: -0.0000

Data Index: 781732 (C4 (Web Text))

Max Activating Token Index: 63

Text #6

Max Range: 0.5140. Min Range: -0.5140

Max Act: 0.3565. Min Act: -0.0000

Data Index: 814997 (C4 (Web Text))

Max Activating Token Index: 561

Text #7

Max Range: 0.5140. Min Range: -0.5140

Max Act: 0.3570. Min Act: -0.0001

Data Index: 980078 (C4 (Web Text))

Max Activating Token Index: 972

Text #8

Max Range: 0.5140. Min Range: -0.5140

Max Act: 0.3690. Min Act: -0.0000

Data Index: 1224408 (C4 (Web Text))

Max Activating Token Index: 413

Text #9

Max Range: 0.5140. Min Range: -0.5140

Max Act: 0.3423. Min Act: -0.0001

Data Index: 1254083 (C4 (Web Text))

Max Activating Token Index: 923

Text #10

Max Range: 0.5140. Min Range: -0.5140

Max Act: 0.3695. Min Act: -0.0000

Data Index: 1128395 (C4 (Web Text))

Max Activating Token Index: 1013

Text #11

Max Range: 0.5140. Min Range: -0.5140

Max Act: 0.3585. Min Act: -0.0000

Data Index: 685479 (C4 (Web Text))

Max Activating Token Index: 112

Text #12

Max Range: 0.5140. Min Range: -0.5140

Max Act: 0.3459. Min Act: -0.0000

Data Index: 597062 (C4 (Web Text))

Max Activating Token Index: 697

Text #13

Max Range: 0.5140. Min Range: -0.5140

Max Act: 0.3632. Min Act: -0.0000

Data Index: 1301699 (C4 (Web Text))

Max Activating Token Index: 319

Text #14

Max Range: 0.5140. Min Range: -0.5140

Max Act: 0.3246. Min Act: -0.0000

Data Index: 301311 (C4 (Web Text))

Max Activating Token Index: 872

Text #15

Max Range: 0.5140. Min Range: -0.5140

Max Act: 0.3256. Min Act: -0.0000

Data Index: 1106271 (C4 (Web Text))

Max Activating Token Index: 420

Text #16

Max Range: 0.5140. Min Range: -0.5140

Max Act: 0.2880. Min Act: -0.0000

Data Index: 1303781 (C4 (Web Text))

Max Activating Token Index: 350

Text #17

Max Range: 0.5140. Min Range: -0.5140

Max Act: 0.3281. Min Act: -0.0000

Data Index: 923556 (C4 (Web Text))

Max Activating Token Index: 160

Text #18

Max Range: 0.5140. Min Range: -0.5140

Max Act: 0.2995. Min Act: -0.0000

Data Index: 44790 (C4 (Web Text))

Max Activating Token Index: 492

Text #19

Max Range: 0.5140. Min Range: -0.5140

Max Act: 0.2981. Min Act: -0.0000

Data Index: 1284335 (C4 (Web Text))

Max Activating Token Index: 709