Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1372 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.7120. Min Range: -0.7120

Max Act: 0.6846. Min Act: -0.0000

Data Index: 1088883 (C4 (Web Text))

Max Activating Token Index: 687

Text #1

Max Range: 0.7120. Min Range: -0.7120

Max Act: 0.7120. Min Act: -0.0000

Data Index: 1256341 (C4 (Web Text))

Max Activating Token Index: 67

Text #2

Max Range: 0.7120. Min Range: -0.7120

Max Act: 0.6580. Min Act: -0.0000

Data Index: 1308864 (C4 (Web Text))

Max Activating Token Index: 669

Text #3

Max Range: 0.7120. Min Range: -0.7120

Max Act: 0.6323. Min Act: -0.0000

Data Index: 189566 (C4 (Web Text))

Max Activating Token Index: 208

Text #4

Max Range: 0.7120. Min Range: -0.7120

Max Act: 0.6288. Min Act: -0.0000

Data Index: 1277566 (C4 (Web Text))

Max Activating Token Index: 986

Text #5

Max Range: 0.7120. Min Range: -0.7120

Max Act: 0.6134. Min Act: -0.0000

Data Index: 922284 (C4 (Web Text))

Max Activating Token Index: 27

Text #6

Max Range: 0.7120. Min Range: -0.7120

Max Act: 0.6046. Min Act: -0.0000

Data Index: 979303 (C4 (Web Text))

Max Activating Token Index: 887

Text #7

Max Range: 0.7120. Min Range: -0.7120

Max Act: 0.5557. Min Act: -0.0000

Data Index: 202944 (C4 (Web Text))

Max Activating Token Index: 893

Text #8

Max Range: 0.7120. Min Range: -0.7120

Max Act: 0.5898. Min Act: -0.0000

Data Index: 238829 (C4 (Web Text))

Max Activating Token Index: 81

Text #9

Max Range: 0.7120. Min Range: -0.7120

Max Act: 0.5585. Min Act: -0.0000

Data Index: 1239085 (C4 (Web Text))

Max Activating Token Index: 52

Text #10

Max Range: 0.7120. Min Range: -0.7120

Max Act: 0.5389. Min Act: -0.0000

Data Index: 180996 (C4 (Web Text))

Max Activating Token Index: 1012

Text #11

Max Range: 0.7120. Min Range: -0.7120

Max Act: 0.5213. Min Act: -0.0000

Data Index: 531034 (C4 (Web Text))

Max Activating Token Index: 515

Text #12

Max Range: 0.7120. Min Range: -0.7120

Max Act: 0.5636. Min Act: -0.0000

Data Index: 960739 (C4 (Web Text))

Max Activating Token Index: 679

Text #13

Max Range: 0.7120. Min Range: -0.7120

Max Act: 0.5110. Min Act: -0.0000

Data Index: 1343729 (C4 (Web Text))

Max Activating Token Index: 498

Text #14

Max Range: 0.7120. Min Range: -0.7120

Max Act: 0.4777. Min Act: -0.0000

Data Index: 1239269 (C4 (Web Text))

Max Activating Token Index: 696

Text #15

Max Range: 0.7120. Min Range: -0.7120

Max Act: 0.5357. Min Act: -0.0000

Data Index: 24145 (C4 (Web Text))

Max Activating Token Index: 446

Text #16

Max Range: 0.7120. Min Range: -0.7120

Max Act: 0.5213. Min Act: -0.0000

Data Index: 481121 (C4 (Web Text))

Max Activating Token Index: 760

Text #17

Max Range: 0.7120. Min Range: -0.7120

Max Act: 0.5119. Min Act: -0.0000

Data Index: 587798 (C4 (Web Text))

Max Activating Token Index: 548

Text #18

Max Range: 0.7120. Min Range: -0.7120

Max Act: 0.5089. Min Act: -0.0000

Data Index: 77994 (C4 (Web Text))

Max Activating Token Index: 111

Text #19

Max Range: 0.7120. Min Range: -0.7120

Max Act: 0.4881. Min Act: -0.0000

Data Index: 1325704 (C4 (Web Text))

Max Activating Token Index: 90