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

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

Neuron 4790 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: 0.3916. Min Range: -0.3916

Max Act: 0.3916. Min Act: -0.0000

Data Index: 1336864 (C4 (Web Text))

Max Activating Token Index: 828

Text #1

Max Range: 0.3916. Min Range: -0.3916

Max Act: 0.3900. Min Act: -0.0000

Data Index: 826112 (C4 (Web Text))

Max Activating Token Index: 651

Text #2

Max Range: 0.3916. Min Range: -0.3916

Max Act: 0.3647. Min Act: -0.0000

Data Index: 380720 (C4 (Web Text))

Max Activating Token Index: 522

Text #3

Max Range: 0.3916. Min Range: -0.3916

Max Act: 0.3604. Min Act: -0.0000

Data Index: 370129 (C4 (Web Text))

Max Activating Token Index: 527

Text #4

Max Range: 0.3916. Min Range: -0.3916

Max Act: 0.3481. Min Act: -0.0000

Data Index: 836896 (C4 (Web Text))

Max Activating Token Index: 190

Text #5

Max Range: 0.3916. Min Range: -0.3916

Max Act: 0.3670. Min Act: -0.0000

Data Index: 684803 (C4 (Web Text))

Max Activating Token Index: 534

Text #6

Max Range: 0.3916. Min Range: -0.3916

Max Act: 0.3690. Min Act: -0.0000

Data Index: 1343699 (C4 (Web Text))

Max Activating Token Index: 204

Text #7

Max Range: 0.3916. Min Range: -0.3916

Max Act: 0.3524. Min Act: -0.0000

Data Index: 822468 (C4 (Web Text))

Max Activating Token Index: 172

Text #8

Max Range: 0.3916. Min Range: -0.3916

Max Act: 0.3275. Min Act: -0.0000

Data Index: 1655418 (Python Code)

Max Activating Token Index: 763

Text #9

Max Range: 0.3916. Min Range: -0.3916

Max Act: 0.3210. Min Act: -0.0000

Data Index: 400130 (C4 (Web Text))

Max Activating Token Index: 527

Text #10

Max Range: 0.3916. Min Range: -0.3916

Max Act: 0.3244. Min Act: -0.0000

Data Index: 360553 (C4 (Web Text))

Max Activating Token Index: 911

Text #11

Max Range: 0.3916. Min Range: -0.3916

Max Act: 0.3188. Min Act: -0.0000

Data Index: 741179 (C4 (Web Text))

Max Activating Token Index: 677

Text #12

Max Range: 0.3916. Min Range: -0.3916

Max Act: 0.3290. Min Act: -0.0000

Data Index: 787215 (C4 (Web Text))

Max Activating Token Index: 560

Text #13

Max Range: 0.3916. Min Range: -0.3916

Max Act: 0.3240. Min Act: -0.0000

Data Index: 1500898 (Python Code)

Max Activating Token Index: 577

Text #14

Max Range: 0.3916. Min Range: -0.3916

Max Act: 0.3096. Min Act: -0.0000

Data Index: 1173083 (C4 (Web Text))

Max Activating Token Index: 401

Text #15

Max Range: 0.3916. Min Range: -0.3916

Max Act: 0.3147. Min Act: -0.0000

Data Index: 1124163 (C4 (Web Text))

Max Activating Token Index: 410

Text #16

Max Range: 0.3916. Min Range: -0.3916

Max Act: 0.3035. Min Act: -0.0000

Data Index: 1266822 (C4 (Web Text))

Max Activating Token Index: 391

Text #17

Max Range: 0.3916. Min Range: -0.3916

Max Act: 0.3044. Min Act: -0.0000

Data Index: 97618 (C4 (Web Text))

Max Activating Token Index: 424

Text #18

Max Range: 0.3916. Min Range: -0.3916

Max Act: 0.3115. Min Act: -0.0000

Data Index: 424552 (C4 (Web Text))

Max Activating Token Index: 123

Text #19

Max Range: 0.3916. Min Range: -0.3916

Max Act: 0.3146. Min Act: -0.0000

Data Index: 1357341 (C4 (Web Text))

Max Activating Token Index: 751