Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3082 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.6911. Min Range: -0.6911

Max Act: 0.6911. Min Act: -0.0000

Data Index: 1632390 (Python Code)

Max Activating Token Index: 853

Text #1

Max Range: 0.6911. Min Range: -0.6911

Max Act: 0.6789. Min Act: -0.0000

Data Index: 227189 (C4 (Web Text))

Max Activating Token Index: 420

Text #2

Max Range: 0.6911. Min Range: -0.6911

Max Act: 0.6038. Min Act: -0.0000

Data Index: 1586166 (Python Code)

Max Activating Token Index: 881

Text #3

Max Range: 0.6911. Min Range: -0.6911

Max Act: 0.6201. Min Act: -0.0000

Data Index: 1587965 (Python Code)

Max Activating Token Index: 127

Text #4

Max Range: 0.6911. Min Range: -0.6911

Max Act: 0.5750. Min Act: -0.0000

Data Index: 1545733 (Python Code)

Max Activating Token Index: 542

Text #5

Max Range: 0.6911. Min Range: -0.6911

Max Act: 0.5681. Min Act: -0.0001

Data Index: 1468886 (Python Code)

Max Activating Token Index: 720

Text #6

Max Range: 0.6911. Min Range: -0.6911

Max Act: 0.5481. Min Act: -0.0001

Data Index: 1481640 (Python Code)

Max Activating Token Index: 788

Text #7

Max Range: 0.6911. Min Range: -0.6911

Max Act: 0.4720. Min Act: -0.0000

Data Index: 1524897 (Python Code)

Max Activating Token Index: 210

Text #8

Max Range: 0.6911. Min Range: -0.6911

Max Act: 0.4797. Min Act: -0.0000

Data Index: 1408053 (Python Code)

Max Activating Token Index: 754

Text #9

Max Range: 0.6911. Min Range: -0.6911

Max Act: 0.4756. Min Act: -0.0000

Data Index: 1529639 (Python Code)

Max Activating Token Index: 120

Text #10

Max Range: 0.6911. Min Range: -0.6911

Max Act: 0.4719. Min Act: -0.0000

Data Index: 1634101 (Python Code)

Max Activating Token Index: 986

Text #11

Max Range: 0.6911. Min Range: -0.6911

Max Act: 0.4517. Min Act: -0.0000

Data Index: 403170 (C4 (Web Text))

Max Activating Token Index: 789

Text #12

Max Range: 0.6911. Min Range: -0.6911

Max Act: 0.4644. Min Act: -0.0000

Data Index: 1476154 (Python Code)

Max Activating Token Index: 306

Text #13

Max Range: 0.6911. Min Range: -0.6911

Max Act: 0.4637. Min Act: -0.0000

Data Index: 1542263 (Python Code)

Max Activating Token Index: 893

Text #14

Max Range: 0.6911. Min Range: -0.6911

Max Act: 0.4549. Min Act: -0.0000

Data Index: 1546461 (Python Code)

Max Activating Token Index: 212

Text #15

Max Range: 0.6911. Min Range: -0.6911

Max Act: 0.4276. Min Act: -0.0000

Data Index: 1535758 (Python Code)

Max Activating Token Index: 295

Text #16

Max Range: 0.6911. Min Range: -0.6911

Max Act: 0.4287. Min Act: -0.0000

Data Index: 1463347 (Python Code)

Max Activating Token Index: 783

Text #17

Max Range: 0.6911. Min Range: -0.6911

Max Act: 0.4443. Min Act: -0.0000

Data Index: 1401544 (Python Code)

Max Activating Token Index: 132

Text #18

Max Range: 0.6911. Min Range: -0.6911

Max Act: 0.4315. Min Act: -0.0000

Data Index: 1425572 (Python Code)

Max Activating Token Index: 229

Text #19

Max Range: 0.6911. Min Range: -0.6911

Max Act: 0.4225. Min Act: -0.0000

Data Index: 1652650 (Python Code)

Max Activating Token Index: 331