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

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

Neuron 2277 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: 0.9483. Min Range: -0.9483

Max Act: 0.9483. Min Act: -0.0000

Data Index: 801667 (C4 (Web Text))

Max Activating Token Index: 83

Text #1

Max Range: 0.9483. Min Range: -0.9483

Max Act: 0.8357. Min Act: -0.0000

Data Index: 925533 (C4 (Web Text))

Max Activating Token Index: 748

Text #2

Max Range: 0.9483. Min Range: -0.9483

Max Act: 0.8819. Min Act: -0.0000

Data Index: 558245 (C4 (Web Text))

Max Activating Token Index: 564

Text #3

Max Range: 0.9483. Min Range: -0.9483

Max Act: 0.8282. Min Act: -0.0000

Data Index: 1018628 (C4 (Web Text))

Max Activating Token Index: 999

Text #4

Max Range: 0.9483. Min Range: -0.9483

Max Act: 0.8710. Min Act: -0.0000

Data Index: 1062654 (C4 (Web Text))

Max Activating Token Index: 196

Text #5

Max Range: 0.9483. Min Range: -0.9483

Max Act: 0.8032. Min Act: -0.0000

Data Index: 1054111 (C4 (Web Text))

Max Activating Token Index: 372

Text #6

Max Range: 0.9483. Min Range: -0.9483

Max Act: 0.8081. Min Act: -0.0000

Data Index: 1131194 (C4 (Web Text))

Max Activating Token Index: 298

Text #7

Max Range: 0.9483. Min Range: -0.9483

Max Act: 0.8072. Min Act: -0.0000

Data Index: 1332154 (C4 (Web Text))

Max Activating Token Index: 36

Text #8

Max Range: 0.9483. Min Range: -0.9483

Max Act: 0.7408. Min Act: -0.0000

Data Index: 87704 (C4 (Web Text))

Max Activating Token Index: 574

Text #9

Max Range: 0.9483. Min Range: -0.9483

Max Act: 0.7845. Min Act: -0.0000

Data Index: 85548 (C4 (Web Text))

Max Activating Token Index: 133

Text #10

Max Range: 0.9483. Min Range: -0.9483

Max Act: 0.7576. Min Act: -0.0000

Data Index: 540046 (C4 (Web Text))

Max Activating Token Index: 195

Text #11

Max Range: 0.9483. Min Range: -0.9483

Max Act: 0.7771. Min Act: -0.0000

Data Index: 1507437 (Python Code)

Max Activating Token Index: 137

Text #12

Max Range: 0.9483. Min Range: -0.9483

Max Act: 0.7928. Min Act: -0.0000

Data Index: 900589 (C4 (Web Text))

Max Activating Token Index: 352

Text #13

Max Range: 0.9483. Min Range: -0.9483

Max Act: 0.7554. Min Act: -0.0000

Data Index: 147992 (C4 (Web Text))

Max Activating Token Index: 602

Text #14

Max Range: 0.9483. Min Range: -0.9483

Max Act: 0.7641. Min Act: -0.0000

Data Index: 346341 (C4 (Web Text))

Max Activating Token Index: 428

Text #15

Max Range: 0.9483. Min Range: -0.9483

Max Act: 0.7691. Min Act: -0.0000

Data Index: 906937 (C4 (Web Text))

Max Activating Token Index: 145

Text #16

Max Range: 0.9483. Min Range: -0.9483

Max Act: 0.7974. Min Act: -0.0000

Data Index: 1331805 (C4 (Web Text))

Max Activating Token Index: 752

Text #17

Max Range: 0.9483. Min Range: -0.9483

Max Act: 0.7516. Min Act: -0.0000

Data Index: 1086810 (C4 (Web Text))

Max Activating Token Index: 973

Text #18

Max Range: 0.9483. Min Range: -0.9483

Max Act: 0.7543. Min Act: -0.0000

Data Index: 1017194 (C4 (Web Text))

Max Activating Token Index: 290

Text #19

Max Range: 0.9483. Min Range: -0.9483

Max Act: 0.7443. Min Act: -0.0000

Data Index: 197968 (C4 (Web Text))

Max Activating Token Index: 187