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

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

Neuron 3633 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: 2.6383. Min Range: -2.6383

Max Act: 2.6383. Min Act: -0.0000

Data Index: 1463444 (Python Code)

Max Activating Token Index: 101

Text #1

Max Range: 2.6383. Min Range: -2.6383

Max Act: 2.5485. Min Act: -0.0000

Data Index: 1592025 (Python Code)

Max Activating Token Index: 322

Text #2

Max Range: 2.6383. Min Range: -2.6383

Max Act: 2.4001. Min Act: -0.0000

Data Index: 1483596 (Python Code)

Max Activating Token Index: 930

Text #3

Max Range: 2.6383. Min Range: -2.6383

Max Act: 2.4628. Min Act: 0.0001

Data Index: 1526797 (Python Code)

Max Activating Token Index: 1000

Text #4

Max Range: 2.6383. Min Range: -2.6383

Max Act: 2.5357. Min Act: -0.0000

Data Index: 1497164 (Python Code)

Max Activating Token Index: 552

Text #5

Max Range: 2.6383. Min Range: -2.6383

Max Act: 2.3120. Min Act: -0.0000

Data Index: 1566247 (Python Code)

Max Activating Token Index: 611

Text #6

Max Range: 2.6383. Min Range: -2.6383

Max Act: 2.2037. Min Act: -0.0000

Data Index: 1497820 (Python Code)

Max Activating Token Index: 63

Text #7

Max Range: 2.6383. Min Range: -2.6383

Max Act: 2.0856. Min Act: -0.0000

Data Index: 1538087 (Python Code)

Max Activating Token Index: 650

Text #8

Max Range: 2.6383. Min Range: -2.6383

Max Act: 2.1904. Min Act: -0.0000

Data Index: 1363662 (Python Code)

Max Activating Token Index: 606

Text #9

Max Range: 2.6383. Min Range: -2.6383

Max Act: 2.0482. Min Act: -0.0000

Data Index: 1369356 (Python Code)

Max Activating Token Index: 1012

Text #10

Max Range: 2.6383. Min Range: -2.6383

Max Act: 1.8986. Min Act: -0.0000

Data Index: 1492701 (Python Code)

Max Activating Token Index: 657

Text #11

Max Range: 2.6383. Min Range: -2.6383

Max Act: 2.1275. Min Act: -0.0000

Data Index: 1401144 (Python Code)

Max Activating Token Index: 133

Text #12

Max Range: 2.6383. Min Range: -2.6383

Max Act: 2.0048. Min Act: -0.0000

Data Index: 1392954 (Python Code)

Max Activating Token Index: 705

Text #13

Max Range: 2.6383. Min Range: -2.6383

Max Act: 1.9935. Min Act: -0.0000

Data Index: 1588481 (Python Code)

Max Activating Token Index: 359

Text #14

Max Range: 2.6383. Min Range: -2.6383

Max Act: 2.0709. Min Act: -0.0000

Data Index: 1545923 (Python Code)

Max Activating Token Index: 698

Text #15

Max Range: 2.6383. Min Range: -2.6383

Max Act: 2.0328. Min Act: -0.0000

Data Index: 1534936 (Python Code)

Max Activating Token Index: 223

Text #16

Max Range: 2.6383. Min Range: -2.6383

Max Act: 1.9136. Min Act: -0.0000

Data Index: 1540740 (Python Code)

Max Activating Token Index: 616

Text #17

Max Range: 2.6383. Min Range: -2.6383

Max Act: 1.9997. Min Act: -0.0000

Data Index: 1656680 (Python Code)

Max Activating Token Index: 238

Text #18

Max Range: 2.6383. Min Range: -2.6383

Max Act: 1.9729. Min Act: -0.0000

Data Index: 1571483 (Python Code)

Max Activating Token Index: 240

Text #19

Max Range: 2.6383. Min Range: -2.6383

Max Act: 1.8423. Min Act: -0.0000

Data Index: 1444166 (Python Code)

Max Activating Token Index: 313