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

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

Neuron 2008 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.8131. Min Range: -4.8131

Max Act: 4.8131. Min Act: -0.0000

Data Index: 1211028 (C4 (Web Text))

Max Activating Token Index: 591

Text #1

Max Range: 4.8131. Min Range: -4.8131

Max Act: 4.4462. Min Act: -0.0000

Data Index: 282200 (C4 (Web Text))

Max Activating Token Index: 970

Text #2

Max Range: 4.8131. Min Range: -4.8131

Max Act: 4.1872. Min Act: -0.0000

Data Index: 856647 (C4 (Web Text))

Max Activating Token Index: 662

Text #3

Max Range: 4.8131. Min Range: -4.8131

Max Act: 4.0433. Min Act: -0.0000

Data Index: 327608 (C4 (Web Text))

Max Activating Token Index: 122

Text #4

Max Range: 4.8131. Min Range: -4.8131

Max Act: 4.1815. Min Act: -0.0000

Data Index: 515073 (C4 (Web Text))

Max Activating Token Index: 780

Text #5

Max Range: 4.8131. Min Range: -4.8131

Max Act: 3.9304. Min Act: -0.0000

Data Index: 275203 (C4 (Web Text))

Max Activating Token Index: 24

Text #6

Max Range: 4.8131. Min Range: -4.8131

Max Act: 3.7518. Min Act: -0.0000

Data Index: 1273209 (C4 (Web Text))

Max Activating Token Index: 318

Text #7

Max Range: 4.8131. Min Range: -4.8131

Max Act: 3.9087. Min Act: -0.0000

Data Index: 121327 (C4 (Web Text))

Max Activating Token Index: 57

Text #8

Max Range: 4.8131. Min Range: -4.8131

Max Act: 3.7493. Min Act: -0.0000

Data Index: 785683 (C4 (Web Text))

Max Activating Token Index: 62

Text #9

Max Range: 4.8131. Min Range: -4.8131

Max Act: 3.6065. Min Act: -0.0000

Data Index: 1291995 (C4 (Web Text))

Max Activating Token Index: 650

Text #10

Max Range: 4.8131. Min Range: -4.8131

Max Act: 3.6241. Min Act: -0.0000

Data Index: 804164 (C4 (Web Text))

Max Activating Token Index: 1010

Text #11

Max Range: 4.8131. Min Range: -4.8131

Max Act: 3.5863. Min Act: -0.0000

Data Index: 349029 (C4 (Web Text))

Max Activating Token Index: 31

Text #12

Max Range: 4.8131. Min Range: -4.8131

Max Act: 3.3795. Min Act: -0.0000

Data Index: 526928 (C4 (Web Text))

Max Activating Token Index: 635

Text #13

Max Range: 4.8131. Min Range: -4.8131

Max Act: 3.6817. Min Act: -0.0000

Data Index: 936390 (C4 (Web Text))

Max Activating Token Index: 974

Text #14

Max Range: 4.8131. Min Range: -4.8131

Max Act: 3.1598. Min Act: -0.0000

Data Index: 123581 (C4 (Web Text))

Max Activating Token Index: 421

Text #15

Max Range: 4.8131. Min Range: -4.8131

Max Act: 3.4889. Min Act: -0.0000

Data Index: 893762 (C4 (Web Text))

Max Activating Token Index: 61

Text #16

Max Range: 4.8131. Min Range: -4.8131

Max Act: 3.4421. Min Act: -0.0000

Data Index: 878383 (C4 (Web Text))

Max Activating Token Index: 422

Text #17

Max Range: 4.8131. Min Range: -4.8131

Max Act: 3.2617. Min Act: -0.0000

Data Index: 739569 (C4 (Web Text))

Max Activating Token Index: 978

Text #18

Max Range: 4.8131. Min Range: -4.8131

Max Act: 3.3565. Min Act: -0.0000

Data Index: 901529 (C4 (Web Text))

Max Activating Token Index: 413

Text #19

Max Range: 4.8131. Min Range: -4.8131

Max Act: 3.3363. Min Act: -0.0000

Data Index: 752933 (C4 (Web Text))

Max Activating Token Index: 306