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

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

Neuron 1383 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: 1.8748. Min Range: -1.8748

Max Act: 1.8748. Min Act: -0.0000

Data Index: 350100 (C4 (Web Text))

Max Activating Token Index: 500

Text #1

Max Range: 1.8748. Min Range: -1.8748

Max Act: 1.6465. Min Act: -0.0000

Data Index: 33124 (C4 (Web Text))

Max Activating Token Index: 831

Text #2

Max Range: 1.8748. Min Range: -1.8748

Max Act: 1.7854. Min Act: -0.0000

Data Index: 665850 (C4 (Web Text))

Max Activating Token Index: 877

Text #3

Max Range: 1.8748. Min Range: -1.8748

Max Act: 1.7853. Min Act: -0.0000

Data Index: 1163822 (C4 (Web Text))

Max Activating Token Index: 489

Text #4

Max Range: 1.8748. Min Range: -1.8748

Max Act: 1.5949. Min Act: -0.0000

Data Index: 562159 (C4 (Web Text))

Max Activating Token Index: 734

Text #5

Max Range: 1.8748. Min Range: -1.8748

Max Act: 1.5583. Min Act: -0.0000

Data Index: 431805 (C4 (Web Text))

Max Activating Token Index: 94

Text #6

Max Range: 1.8748. Min Range: -1.8748

Max Act: 1.6159. Min Act: -0.0000

Data Index: 1079317 (C4 (Web Text))

Max Activating Token Index: 929

Text #7

Max Range: 1.8748. Min Range: -1.8748

Max Act: 1.5888. Min Act: -0.0000

Data Index: 630100 (C4 (Web Text))

Max Activating Token Index: 806

Text #8

Max Range: 1.8748. Min Range: -1.8748

Max Act: 1.4531. Min Act: -0.0000

Data Index: 677688 (C4 (Web Text))

Max Activating Token Index: 463

Text #9

Max Range: 1.8748. Min Range: -1.8748

Max Act: 1.4797. Min Act: -0.0000

Data Index: 1289115 (C4 (Web Text))

Max Activating Token Index: 399

Text #10

Max Range: 1.8748. Min Range: -1.8748

Max Act: 1.4638. Min Act: -0.0000

Data Index: 65561 (C4 (Web Text))

Max Activating Token Index: 536

Text #11

Max Range: 1.8748. Min Range: -1.8748

Max Act: 1.4532. Min Act: -0.0000

Data Index: 562509 (C4 (Web Text))

Max Activating Token Index: 696

Text #12

Max Range: 1.8748. Min Range: -1.8748

Max Act: 1.4141. Min Act: -0.0000

Data Index: 612447 (C4 (Web Text))

Max Activating Token Index: 1001

Text #13

Max Range: 1.8748. Min Range: -1.8748

Max Act: 1.4066. Min Act: -0.0000

Data Index: 420038 (C4 (Web Text))

Max Activating Token Index: 672

Text #14

Max Range: 1.8748. Min Range: -1.8748

Max Act: 1.3250. Min Act: -0.0000

Data Index: 174742 (C4 (Web Text))

Max Activating Token Index: 129

Text #15

Max Range: 1.8748. Min Range: -1.8748

Max Act: 1.4029. Min Act: -0.0000

Data Index: 1239861 (C4 (Web Text))

Max Activating Token Index: 858

Text #16

Max Range: 1.8748. Min Range: -1.8748

Max Act: 1.4773. Min Act: -0.0000

Data Index: 984740 (C4 (Web Text))

Max Activating Token Index: 919

Text #17

Max Range: 1.8748. Min Range: -1.8748

Max Act: 1.4708. Min Act: -0.0000

Data Index: 322025 (C4 (Web Text))

Max Activating Token Index: 412

Text #18

Max Range: 1.8748. Min Range: -1.8748

Max Act: 1.4702. Min Act: -0.0000

Data Index: 1194045 (C4 (Web Text))

Max Activating Token Index: 242

Text #19

Max Range: 1.8748. Min Range: -1.8748

Max Act: 1.3579. Min Act: -0.0000

Data Index: 1142331 (C4 (Web Text))

Max Activating Token Index: 756