Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1198 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 4.6120. Min Range: -4.6120

Max Act: 4.6120. Min Act: -0.0006

Data Index: 1385715 (Python Code)

Max Activating Token Index: 222

Text #1

Max Range: 4.6120. Min Range: -4.6120

Max Act: 1.6254. Min Act: -0.0006

Data Index: 1037468 (C4 (Web Text))

Max Activating Token Index: 9

Text #2

Max Range: 4.6120. Min Range: -4.6120

Max Act: 3.2119. Min Act: -0.0006

Data Index: 1595659 (Python Code)

Max Activating Token Index: 32

Text #3

Max Range: 4.6120. Min Range: -4.6120

Max Act: 0.7816. Min Act: -0.0006

Data Index: 360661 (C4 (Web Text))

Max Activating Token Index: 7

Text #4

Max Range: 4.6120. Min Range: -4.6120

Max Act: 2.8455. Min Act: -0.0006

Data Index: 1620448 (Python Code)

Max Activating Token Index: 143

Text #5

Max Range: 4.6120. Min Range: -4.6120

Max Act: 2.4156. Min Act: -0.0006

Data Index: 888102 (C4 (Web Text))

Max Activating Token Index: 2

Text #6

Max Range: 4.6120. Min Range: -4.6120

Max Act: 2.0056. Min Act: -0.0006

Data Index: 1281492 (C4 (Web Text))

Max Activating Token Index: 6

Text #7

Max Range: 4.6120. Min Range: -4.6120

Max Act: 2.4587. Min Act: -0.0006

Data Index: 1504280 (Python Code)

Max Activating Token Index: 85

Text #8

Max Range: 4.6120. Min Range: -4.6120

Max Act: 1.2448. Min Act: -0.0006

Data Index: 1641725 (Python Code)

Max Activating Token Index: 2

Text #9

Max Range: 4.6120. Min Range: -4.6120

Max Act: 0.2719. Min Act: -0.0006

Data Index: 63993 (C4 (Web Text))

Max Activating Token Index: 10

Text #10

Max Range: 4.6120. Min Range: -4.6120

Max Act: 0.4939. Min Act: -0.0006

Data Index: 534100 (C4 (Web Text))

Max Activating Token Index: 4

Text #11

Max Range: 4.6120. Min Range: -4.6120

Max Act: 1.2151. Min Act: -0.0005

Data Index: 30296 (C4 (Web Text))

Max Activating Token Index: 5

Text #12

Max Range: 4.6120. Min Range: -4.6120

Max Act: 0.2668. Min Act: -0.0006

Data Index: 296147 (C4 (Web Text))

Max Activating Token Index: 10

Text #13

Max Range: 4.6120. Min Range: -4.6120

Max Act: 0.3340. Min Act: -0.0006

Data Index: 627254 (C4 (Web Text))

Max Activating Token Index: 9

Text #14

Max Range: 4.6120. Min Range: -4.6120

Max Act: 0.4200. Min Act: -0.0006

Data Index: 919090 (C4 (Web Text))

Max Activating Token Index: 952

Text #15

Max Range: 4.6120. Min Range: -4.6120

Max Act: 0.2813. Min Act: -0.0006

Data Index: 1445175 (Python Code)

Max Activating Token Index: 6

Text #16

Max Range: 4.6120. Min Range: -4.6120

Max Act: 0.3744. Min Act: -0.0005

Data Index: 1587603 (Python Code)

Max Activating Token Index: 306

Text #17

Max Range: 4.6120. Min Range: -4.6120

Max Act: 0.2017. Min Act: -0.0006

Data Index: 27370 (C4 (Web Text))

Max Activating Token Index: 842

Text #18

Max Range: 4.6120. Min Range: -4.6120

Max Act: 0.3923. Min Act: -0.0005

Data Index: 1533839 (Python Code)

Max Activating Token Index: 143

Text #19

Max Range: 4.6120. Min Range: -4.6120

Max Act: 0.3517. Min Act: -0.0006

Data Index: 557620 (C4 (Web Text))

Max Activating Token Index: 98