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

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

Neuron 555 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: 0.9579. Min Range: -0.9579

Max Act: 0.9579. Min Act: -0.0000

Data Index: 914302 (C4 (Web Text))

Max Activating Token Index: 535

Text #1

Max Range: 0.9579. Min Range: -0.9579

Max Act: 0.8648. Min Act: -0.0000

Data Index: 53688 (C4 (Web Text))

Max Activating Token Index: 370

Text #2

Max Range: 0.9579. Min Range: -0.9579

Max Act: 0.6972. Min Act: -0.0000

Data Index: 915175 (C4 (Web Text))

Max Activating Token Index: 963

Text #3

Max Range: 0.9579. Min Range: -0.9579

Max Act: 0.6751. Min Act: -0.0000

Data Index: 366039 (C4 (Web Text))

Max Activating Token Index: 858

Text #4

Max Range: 0.9579. Min Range: -0.9579

Max Act: 0.6820. Min Act: -0.0000

Data Index: 1356820 (C4 (Web Text))

Max Activating Token Index: 630

Text #5

Max Range: 0.9579. Min Range: -0.9579

Max Act: 0.6669. Min Act: -0.0000

Data Index: 745971 (C4 (Web Text))

Max Activating Token Index: 852

Text #6

Max Range: 0.9579. Min Range: -0.9579

Max Act: 0.6387. Min Act: -0.0000

Data Index: 1217079 (C4 (Web Text))

Max Activating Token Index: 869

Text #7

Max Range: 0.9579. Min Range: -0.9579

Max Act: 0.6534. Min Act: -0.0000

Data Index: 855369 (C4 (Web Text))

Max Activating Token Index: 31

Text #8

Max Range: 0.9579. Min Range: -0.9579

Max Act: 0.6469. Min Act: -0.0000

Data Index: 1007735 (C4 (Web Text))

Max Activating Token Index: 207

Text #9

Max Range: 0.9579. Min Range: -0.9579

Max Act: 0.6448. Min Act: -0.0000

Data Index: 178216 (C4 (Web Text))

Max Activating Token Index: 750

Text #10

Max Range: 0.9579. Min Range: -0.9579

Max Act: 0.5864. Min Act: -0.0000

Data Index: 1160754 (C4 (Web Text))

Max Activating Token Index: 760

Text #11

Max Range: 0.9579. Min Range: -0.9579

Max Act: 0.5696. Min Act: -0.0000

Data Index: 906076 (C4 (Web Text))

Max Activating Token Index: 690

Text #12

Max Range: 0.9579. Min Range: -0.9579

Max Act: 0.5890. Min Act: -0.0000

Data Index: 1189058 (C4 (Web Text))

Max Activating Token Index: 985

Text #13

Max Range: 0.9579. Min Range: -0.9579

Max Act: 0.4710. Min Act: -0.0000

Data Index: 1133717 (C4 (Web Text))

Max Activating Token Index: 895

Text #14

Max Range: 0.9579. Min Range: -0.9579

Max Act: 0.5678. Min Act: -0.0000

Data Index: 392135 (C4 (Web Text))

Max Activating Token Index: 343

Text #15

Max Range: 0.9579. Min Range: -0.9579

Max Act: 0.5582. Min Act: -0.0000

Data Index: 1170851 (C4 (Web Text))

Max Activating Token Index: 938

Text #16

Max Range: 0.9579. Min Range: -0.9579

Max Act: 0.5249. Min Act: -0.0000

Data Index: 280812 (C4 (Web Text))

Max Activating Token Index: 474

Text #17

Max Range: 0.9579. Min Range: -0.9579

Max Act: 0.5082. Min Act: -0.0000

Data Index: 284768 (C4 (Web Text))

Max Activating Token Index: 724

Text #18

Max Range: 0.9579. Min Range: -0.9579

Max Act: 0.4792. Min Act: -0.0000

Data Index: 536605 (C4 (Web Text))

Max Activating Token Index: 696

Text #19

Max Range: 0.9579. Min Range: -0.9579

Max Act: 0.5268. Min Act: -0.0000

Data Index: 1179896 (C4 (Web Text))

Max Activating Token Index: 615