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

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

Neuron 2010 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: 2.3810. Min Range: -2.3810

Max Act: 2.3810. Min Act: -0.0000

Data Index: 352128 (C4 (Web Text))

Max Activating Token Index: 203

Text #1

Max Range: 2.3810. Min Range: -2.3810

Max Act: 2.1552. Min Act: -0.0000

Data Index: 477435 (C4 (Web Text))

Max Activating Token Index: 1008

Text #2

Max Range: 2.3810. Min Range: -2.3810

Max Act: 2.0577. Min Act: -0.0000

Data Index: 721081 (C4 (Web Text))

Max Activating Token Index: 152

Text #3

Max Range: 2.3810. Min Range: -2.3810

Max Act: 1.9398. Min Act: -0.0000

Data Index: 1294122 (C4 (Web Text))

Max Activating Token Index: 411

Text #4

Max Range: 2.3810. Min Range: -2.3810

Max Act: 1.9679. Min Act: -0.0000

Data Index: 97055 (C4 (Web Text))

Max Activating Token Index: 990

Text #5

Max Range: 2.3810. Min Range: -2.3810

Max Act: 1.9671. Min Act: -0.0000

Data Index: 1168723 (C4 (Web Text))

Max Activating Token Index: 923

Text #6

Max Range: 2.3810. Min Range: -2.3810

Max Act: 1.8623. Min Act: -0.0000

Data Index: 977547 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 2.3810. Min Range: -2.3810

Max Act: 1.7178. Min Act: -0.0000

Data Index: 904321 (C4 (Web Text))

Max Activating Token Index: 599

Text #8

Max Range: 2.3810. Min Range: -2.3810

Max Act: 1.6838. Min Act: -0.0000

Data Index: 743644 (C4 (Web Text))

Max Activating Token Index: 596

Text #9

Max Range: 2.3810. Min Range: -2.3810

Max Act: 1.5681. Min Act: -0.0000

Data Index: 180355 (C4 (Web Text))

Max Activating Token Index: 645

Text #10

Max Range: 2.3810. Min Range: -2.3810

Max Act: 1.5688. Min Act: -0.0000

Data Index: 180972 (C4 (Web Text))

Max Activating Token Index: 365

Text #11

Max Range: 2.3810. Min Range: -2.3810

Max Act: 1.6234. Min Act: -0.0000

Data Index: 705901 (C4 (Web Text))

Max Activating Token Index: 840

Text #12

Max Range: 2.3810. Min Range: -2.3810

Max Act: 1.6249. Min Act: -0.0000

Data Index: 1175887 (C4 (Web Text))

Max Activating Token Index: 922

Text #13

Max Range: 2.3810. Min Range: -2.3810

Max Act: 1.4692. Min Act: -0.0000

Data Index: 918260 (C4 (Web Text))

Max Activating Token Index: 761

Text #14

Max Range: 2.3810. Min Range: -2.3810

Max Act: 1.3825. Min Act: -0.0000

Data Index: 1210181 (C4 (Web Text))

Max Activating Token Index: 996

Text #15

Max Range: 2.3810. Min Range: -2.3810

Max Act: 1.4768. Min Act: -0.0000

Data Index: 601056 (C4 (Web Text))

Max Activating Token Index: 254

Text #16

Max Range: 2.3810. Min Range: -2.3810

Max Act: 1.3385. Min Act: -0.0000

Data Index: 1359673 (C4 (Web Text))

Max Activating Token Index: 604

Text #17

Max Range: 2.3810. Min Range: -2.3810

Max Act: 1.4171. Min Act: -0.0000

Data Index: 1002632 (C4 (Web Text))

Max Activating Token Index: 501

Text #18

Max Range: 2.3810. Min Range: -2.3810

Max Act: 1.4139. Min Act: -0.0000

Data Index: 65970 (C4 (Web Text))

Max Activating Token Index: 947

Text #19

Max Range: 2.3810. Min Range: -2.3810

Max Act: 1.4671. Min Act: -0.0000

Data Index: 1259900 (C4 (Web Text))

Max Activating Token Index: 430