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

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

Neuron 93 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: 2.5937. Min Range: -2.5937

Max Act: 2.5937. Min Act: -0.0000

Data Index: 293859 (C4 (Web Text))

Max Activating Token Index: 613

Text #1

Max Range: 2.5937. Min Range: -2.5937

Max Act: 2.3083. Min Act: -0.0000

Data Index: 661085 (C4 (Web Text))

Max Activating Token Index: 632

Text #2

Max Range: 2.5937. Min Range: -2.5937

Max Act: 1.9497. Min Act: -0.0000

Data Index: 636772 (C4 (Web Text))

Max Activating Token Index: 176

Text #3

Max Range: 2.5937. Min Range: -2.5937

Max Act: 1.8918. Min Act: -0.0000

Data Index: 1256153 (C4 (Web Text))

Max Activating Token Index: 76

Text #4

Max Range: 2.5937. Min Range: -2.5937

Max Act: 1.7442. Min Act: -0.0000

Data Index: 547557 (C4 (Web Text))

Max Activating Token Index: 184

Text #5

Max Range: 2.5937. Min Range: -2.5937

Max Act: 1.7714. Min Act: -0.0000

Data Index: 1258356 (C4 (Web Text))

Max Activating Token Index: 511

Text #6

Max Range: 2.5937. Min Range: -2.5937

Max Act: 1.6117. Min Act: -0.0000

Data Index: 717780 (C4 (Web Text))

Max Activating Token Index: 927

Text #7

Max Range: 2.5937. Min Range: -2.5937

Max Act: 1.6968. Min Act: -0.0000

Data Index: 971173 (C4 (Web Text))

Max Activating Token Index: 181

Text #8

Max Range: 2.5937. Min Range: -2.5937

Max Act: 1.5465. Min Act: -0.0000

Data Index: 1071099 (C4 (Web Text))

Max Activating Token Index: 809

Text #9

Max Range: 2.5937. Min Range: -2.5937

Max Act: 1.6328. Min Act: -0.0000

Data Index: 410604 (C4 (Web Text))

Max Activating Token Index: 48

Text #10

Max Range: 2.5937. Min Range: -2.5937

Max Act: 1.6208. Min Act: -0.0000

Data Index: 1341292 (C4 (Web Text))

Max Activating Token Index: 847

Text #11

Max Range: 2.5937. Min Range: -2.5937

Max Act: 1.6119. Min Act: -0.0000

Data Index: 380285 (C4 (Web Text))

Max Activating Token Index: 35

Text #12

Max Range: 2.5937. Min Range: -2.5937

Max Act: 1.5089. Min Act: -0.0000

Data Index: 1237491 (C4 (Web Text))

Max Activating Token Index: 229

Text #13

Max Range: 2.5937. Min Range: -2.5937

Max Act: 1.5547. Min Act: -0.0000

Data Index: 264425 (C4 (Web Text))

Max Activating Token Index: 957

Text #14

Max Range: 2.5937. Min Range: -2.5937

Max Act: 1.6888. Min Act: -0.0000

Data Index: 420144 (C4 (Web Text))

Max Activating Token Index: 952

Text #15

Max Range: 2.5937. Min Range: -2.5937

Max Act: 1.5252. Min Act: -0.0000

Data Index: 1088502 (C4 (Web Text))

Max Activating Token Index: 399

Text #16

Max Range: 2.5937. Min Range: -2.5937

Max Act: 1.4600. Min Act: -0.0000

Data Index: 623173 (C4 (Web Text))

Max Activating Token Index: 31

Text #17

Max Range: 2.5937. Min Range: -2.5937

Max Act: 1.5338. Min Act: -0.0000

Data Index: 1269769 (C4 (Web Text))

Max Activating Token Index: 573

Text #18

Max Range: 2.5937. Min Range: -2.5937

Max Act: 1.4798. Min Act: -0.0000

Data Index: 758645 (C4 (Web Text))

Max Activating Token Index: 361

Text #19

Max Range: 2.5937. Min Range: -2.5937

Max Act: 1.5406. Min Act: -0.0000

Data Index: 886592 (C4 (Web Text))

Max Activating Token Index: 181