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

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

Neuron 4473 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: 2.6413. Min Range: -2.6413

Max Act: 2.6413. Min Act: -0.0000

Data Index: 1000427 (C4 (Web Text))

Max Activating Token Index: 263

Text #1

Max Range: 2.6413. Min Range: -2.6413

Max Act: 1.8950. Min Act: 0.0002

Data Index: 131563 (C4 (Web Text))

Max Activating Token Index: 381

Text #2

Max Range: 2.6413. Min Range: -2.6413

Max Act: 1.3571. Min Act: 0.0002

Data Index: 435821 (C4 (Web Text))

Max Activating Token Index: 90

Text #3

Max Range: 2.6413. Min Range: -2.6413

Max Act: 1.1355. Min Act: -0.0000

Data Index: 59308 (C4 (Web Text))

Max Activating Token Index: 726

Text #4

Max Range: 2.6413. Min Range: -2.6413

Max Act: 1.0398. Min Act: -0.0000

Data Index: 1082816 (C4 (Web Text))

Max Activating Token Index: 115

Text #5

Max Range: 2.6413. Min Range: -2.6413

Max Act: 1.0480. Min Act: -0.0000

Data Index: 1398657 (Python Code)

Max Activating Token Index: 739

Text #6

Max Range: 2.6413. Min Range: -2.6413

Max Act: 0.9654. Min Act: -0.0000

Data Index: 520479 (C4 (Web Text))

Max Activating Token Index: 89

Text #7

Max Range: 2.6413. Min Range: -2.6413

Max Act: 0.9391. Min Act: -0.0000

Data Index: 447042 (C4 (Web Text))

Max Activating Token Index: 921

Text #8

Max Range: 2.6413. Min Range: -2.6413

Max Act: 0.8967. Min Act: 0.0000

Data Index: 403610 (C4 (Web Text))

Max Activating Token Index: 994

Text #9

Max Range: 2.6413. Min Range: -2.6413

Max Act: 0.9361. Min Act: -0.0000

Data Index: 1164822 (C4 (Web Text))

Max Activating Token Index: 960

Text #10

Max Range: 2.6413. Min Range: -2.6413

Max Act: 0.9146. Min Act: -0.0000

Data Index: 416595 (C4 (Web Text))

Max Activating Token Index: 459

Text #11

Max Range: 2.6413. Min Range: -2.6413

Max Act: 0.8675. Min Act: -0.0000

Data Index: 1650545 (Python Code)

Max Activating Token Index: 225

Text #12

Max Range: 2.6413. Min Range: -2.6413

Max Act: 0.8908. Min Act: -0.0000

Data Index: 69051 (C4 (Web Text))

Max Activating Token Index: 965

Text #13

Max Range: 2.6413. Min Range: -2.6413

Max Act: 0.8426. Min Act: -0.0000

Data Index: 950167 (C4 (Web Text))

Max Activating Token Index: 776

Text #14

Max Range: 2.6413. Min Range: -2.6413

Max Act: 0.8118. Min Act: -0.0000

Data Index: 774826 (C4 (Web Text))

Max Activating Token Index: 203

Text #15

Max Range: 2.6413. Min Range: -2.6413

Max Act: 0.8247. Min Act: -0.0000

Data Index: 65829 (C4 (Web Text))

Max Activating Token Index: 373

Text #16

Max Range: 2.6413. Min Range: -2.6413

Max Act: 0.8154. Min Act: -0.0000

Data Index: 1032883 (C4 (Web Text))

Max Activating Token Index: 1001

Text #17

Max Range: 2.6413. Min Range: -2.6413

Max Act: 0.8087. Min Act: -0.0000

Data Index: 44093 (C4 (Web Text))

Max Activating Token Index: 128

Text #18

Max Range: 2.6413. Min Range: -2.6413

Max Act: 0.7720. Min Act: -0.0000

Data Index: 983804 (C4 (Web Text))

Max Activating Token Index: 684

Text #19

Max Range: 2.6413. Min Range: -2.6413

Max Act: 0.7224. Min Act: -0.0000

Data Index: 910968 (C4 (Web Text))

Max Activating Token Index: 610