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

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

Neuron 3500 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4902. Min Range: -0.4902

Max Act: 0.4902. Min Act: -0.0000

Data Index: 649546 (C4 (Web Text))

Max Activating Token Index: 710

Text #1

Max Range: 0.4902. Min Range: -0.4902

Max Act: 0.4614. Min Act: -0.0000

Data Index: 569353 (C4 (Web Text))

Max Activating Token Index: 584

Text #2

Max Range: 0.4902. Min Range: -0.4902

Max Act: 0.4152. Min Act: -0.0000

Data Index: 954601 (C4 (Web Text))

Max Activating Token Index: 178

Text #3

Max Range: 0.4902. Min Range: -0.4902

Max Act: 0.4524. Min Act: -0.0000

Data Index: 792140 (C4 (Web Text))

Max Activating Token Index: 473

Text #4

Max Range: 0.4902. Min Range: -0.4902

Max Act: 0.4097. Min Act: -0.0000

Data Index: 335034 (C4 (Web Text))

Max Activating Token Index: 353

Text #5

Max Range: 0.4902. Min Range: -0.4902

Max Act: 0.3938. Min Act: -0.0000

Data Index: 445241 (C4 (Web Text))

Max Activating Token Index: 1020

Text #6

Max Range: 0.4902. Min Range: -0.4902

Max Act: 0.3883. Min Act: -0.0000

Data Index: 1560508 (Python Code)

Max Activating Token Index: 400

Text #7

Max Range: 0.4902. Min Range: -0.4902

Max Act: 0.3774. Min Act: -0.0000

Data Index: 849213 (C4 (Web Text))

Max Activating Token Index: 429

Text #8

Max Range: 0.4902. Min Range: -0.4902

Max Act: 0.4157. Min Act: -0.0000

Data Index: 1227073 (C4 (Web Text))

Max Activating Token Index: 498

Text #9

Max Range: 0.4902. Min Range: -0.4902

Max Act: 0.3602. Min Act: -0.0000

Data Index: 259518 (C4 (Web Text))

Max Activating Token Index: 188

Text #10

Max Range: 0.4902. Min Range: -0.4902

Max Act: 0.3709. Min Act: -0.0000

Data Index: 910110 (C4 (Web Text))

Max Activating Token Index: 887

Text #11

Max Range: 0.4902. Min Range: -0.4902

Max Act: 0.3685. Min Act: -0.0000

Data Index: 668403 (C4 (Web Text))

Max Activating Token Index: 660

Text #12

Max Range: 0.4902. Min Range: -0.4902

Max Act: 0.3827. Min Act: -0.0000

Data Index: 1090610 (C4 (Web Text))

Max Activating Token Index: 591

Text #13

Max Range: 0.4902. Min Range: -0.4902

Max Act: 0.3482. Min Act: -0.0000

Data Index: 217800 (C4 (Web Text))

Max Activating Token Index: 570

Text #14

Max Range: 0.4902. Min Range: -0.4902

Max Act: 0.3930. Min Act: -0.0000

Data Index: 1027980 (C4 (Web Text))

Max Activating Token Index: 804

Text #15

Max Range: 0.4902. Min Range: -0.4902

Max Act: 0.3582. Min Act: -0.0000

Data Index: 1134552 (C4 (Web Text))

Max Activating Token Index: 590

Text #16

Max Range: 0.4902. Min Range: -0.4902

Max Act: 0.3299. Min Act: -0.0000

Data Index: 1073793 (C4 (Web Text))

Max Activating Token Index: 181

Text #17

Max Range: 0.4902. Min Range: -0.4902

Max Act: 0.3624. Min Act: -0.0000

Data Index: 402637 (C4 (Web Text))

Max Activating Token Index: 524

Text #18

Max Range: 0.4902. Min Range: -0.4902

Max Act: 0.3496. Min Act: -0.0000

Data Index: 1124484 (C4 (Web Text))

Max Activating Token Index: 164

Text #19

Max Range: 0.4902. Min Range: -0.4902

Max Act: 0.3282. Min Act: -0.0000

Data Index: 83674 (C4 (Web Text))

Max Activating Token Index: 630