Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4994 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.6903. Min Range: -0.6903

Max Act: 0.6750. Min Act: -0.0000

Data Index: 1443796 (Python Code)

Max Activating Token Index: 124

Text #1

Max Range: 0.6903. Min Range: -0.6903

Max Act: 0.6903. Min Act: -0.0000

Data Index: 1209420 (C4 (Web Text))

Max Activating Token Index: 1006

Text #2

Max Range: 0.6903. Min Range: -0.6903

Max Act: 0.6419. Min Act: -0.0000

Data Index: 1500498 (Python Code)

Max Activating Token Index: 717

Text #3

Max Range: 0.6903. Min Range: -0.6903

Max Act: 0.6200. Min Act: -0.0000

Data Index: 294614 (C4 (Web Text))

Max Activating Token Index: 721

Text #4

Max Range: 0.6903. Min Range: -0.6903

Max Act: 0.6431. Min Act: -0.0000

Data Index: 206552 (C4 (Web Text))

Max Activating Token Index: 257

Text #5

Max Range: 0.6903. Min Range: -0.6903

Max Act: 0.6701. Min Act: -0.0000

Data Index: 803569 (C4 (Web Text))

Max Activating Token Index: 222

Text #6

Max Range: 0.6903. Min Range: -0.6903

Max Act: 0.6251. Min Act: 0.0000

Data Index: 858152 (C4 (Web Text))

Max Activating Token Index: 123

Text #7

Max Range: 0.6903. Min Range: -0.6903

Max Act: 0.6226. Min Act: -0.0000

Data Index: 896263 (C4 (Web Text))

Max Activating Token Index: 449

Text #8

Max Range: 0.6903. Min Range: -0.6903

Max Act: 0.6669. Min Act: -0.0000

Data Index: 1559364 (Python Code)

Max Activating Token Index: 829

Text #9

Max Range: 0.6903. Min Range: -0.6903

Max Act: 0.6582. Min Act: -0.0000

Data Index: 1122259 (C4 (Web Text))

Max Activating Token Index: 282

Text #10

Max Range: 0.6903. Min Range: -0.6903

Max Act: 0.6275. Min Act: -0.0000

Data Index: 962187 (C4 (Web Text))

Max Activating Token Index: 822

Text #11

Max Range: 0.6903. Min Range: -0.6903

Max Act: 0.6141. Min Act: -0.0000

Data Index: 1481408 (Python Code)

Max Activating Token Index: 762

Text #12

Max Range: 0.6903. Min Range: -0.6903

Max Act: 0.5994. Min Act: -0.0000

Data Index: 1654815 (Python Code)

Max Activating Token Index: 679

Text #13

Max Range: 0.6903. Min Range: -0.6903

Max Act: 0.6051. Min Act: -0.0000

Data Index: 1195301 (C4 (Web Text))

Max Activating Token Index: 518

Text #14

Max Range: 0.6903. Min Range: -0.6903

Max Act: 0.5731. Min Act: -0.0000

Data Index: 403778 (C4 (Web Text))

Max Activating Token Index: 319

Text #15

Max Range: 0.6903. Min Range: -0.6903

Max Act: 0.5553. Min Act: -0.0000

Data Index: 1418862 (Python Code)

Max Activating Token Index: 600

Text #16

Max Range: 0.6903. Min Range: -0.6903

Max Act: 0.5817. Min Act: -0.0000

Data Index: 310964 (C4 (Web Text))

Max Activating Token Index: 235

Text #17

Max Range: 0.6903. Min Range: -0.6903

Max Act: 0.5550. Min Act: -0.0000

Data Index: 1114406 (C4 (Web Text))

Max Activating Token Index: 508

Text #18

Max Range: 0.6903. Min Range: -0.6903

Max Act: 0.5777. Min Act: -0.0000

Data Index: 1511908 (Python Code)

Max Activating Token Index: 927

Text #19

Max Range: 0.6903. Min Range: -0.6903

Max Act: 0.5902. Min Act: -0.0000

Data Index: 138977 (C4 (Web Text))

Max Activating Token Index: 221