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

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

Neuron 4600 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1065. Min Range: -0.1065

Max Act: 0.1065. Min Act: -0.0002

Data Index: 94487 (C4 (Web Text))

Max Activating Token Index: 767

Text #1

Max Range: 0.1065. Min Range: -0.1065

Max Act: 0.1011. Min Act: -0.0002

Data Index: 1229715 (C4 (Web Text))

Max Activating Token Index: 900

Text #2

Max Range: 0.1065. Min Range: -0.1065

Max Act: 0.0975. Min Act: -0.0002

Data Index: 745297 (C4 (Web Text))

Max Activating Token Index: 820

Text #3

Max Range: 0.1065. Min Range: -0.1065

Max Act: 0.1036. Min Act: -0.0002

Data Index: 737476 (C4 (Web Text))

Max Activating Token Index: 482

Text #4

Max Range: 0.1065. Min Range: -0.1065

Max Act: 0.0987. Min Act: -0.0002

Data Index: 1041214 (C4 (Web Text))

Max Activating Token Index: 923

Text #5

Max Range: 0.1065. Min Range: -0.1065

Max Act: 0.0942. Min Act: -0.0002

Data Index: 1178107 (C4 (Web Text))

Max Activating Token Index: 369

Text #6

Max Range: 0.1065. Min Range: -0.1065

Max Act: 0.0861. Min Act: -0.0002

Data Index: 399229 (C4 (Web Text))

Max Activating Token Index: 363

Text #7

Max Range: 0.1065. Min Range: -0.1065

Max Act: 0.0933. Min Act: -0.0002

Data Index: 519844 (C4 (Web Text))

Max Activating Token Index: 318

Text #8

Max Range: 0.1065. Min Range: -0.1065

Max Act: 0.0902. Min Act: -0.0002

Data Index: 442808 (C4 (Web Text))

Max Activating Token Index: 654

Text #9

Max Range: 0.1065. Min Range: -0.1065

Max Act: 0.0974. Min Act: -0.0002

Data Index: 859358 (C4 (Web Text))

Max Activating Token Index: 429

Text #10

Max Range: 0.1065. Min Range: -0.1065

Max Act: 0.0929. Min Act: -0.0002

Data Index: 380155 (C4 (Web Text))

Max Activating Token Index: 429

Text #11

Max Range: 0.1065. Min Range: -0.1065

Max Act: 0.0866. Min Act: -0.0002

Data Index: 1160343 (C4 (Web Text))

Max Activating Token Index: 361

Text #12

Max Range: 0.1065. Min Range: -0.1065

Max Act: 0.0929. Min Act: -0.0002

Data Index: 547439 (C4 (Web Text))

Max Activating Token Index: 408

Text #13

Max Range: 0.1065. Min Range: -0.1065

Max Act: 0.0994. Min Act: -0.0002

Data Index: 847373 (C4 (Web Text))

Max Activating Token Index: 1003

Text #14

Max Range: 0.1065. Min Range: -0.1065

Max Act: 0.0793. Min Act: -0.0002

Data Index: 815353 (C4 (Web Text))

Max Activating Token Index: 852

Text #15

Max Range: 0.1065. Min Range: -0.1065

Max Act: 0.0946. Min Act: -0.0002

Data Index: 858348 (C4 (Web Text))

Max Activating Token Index: 896

Text #16

Max Range: 0.1065. Min Range: -0.1065

Max Act: 0.0936. Min Act: -0.0002

Data Index: 109693 (C4 (Web Text))

Max Activating Token Index: 499

Text #17

Max Range: 0.1065. Min Range: -0.1065

Max Act: 0.0938. Min Act: -0.0002

Data Index: 1190528 (C4 (Web Text))

Max Activating Token Index: 296

Text #18

Max Range: 0.1065. Min Range: -0.1065

Max Act: 0.0897. Min Act: -0.0002

Data Index: 948232 (C4 (Web Text))

Max Activating Token Index: 983

Text #19

Max Range: 0.1065. Min Range: -0.1065

Max Act: 0.0838. Min Act: -0.0002

Data Index: 1250892 (C4 (Web Text))

Max Activating Token Index: 278