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

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

Neuron 1170 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4749. Min Range: -2.4749

Max Act: 2.4749. Min Act: -0.0000

Data Index: 311125 (C4 (Web Text))

Max Activating Token Index: 221

Text #1

Max Range: 2.4749. Min Range: -2.4749

Max Act: 2.4218. Min Act: -0.0000

Data Index: 989230 (C4 (Web Text))

Max Activating Token Index: 697

Text #2

Max Range: 2.4749. Min Range: -2.4749

Max Act: 2.0505. Min Act: -0.0000

Data Index: 1583551 (Python Code)

Max Activating Token Index: 239

Text #3

Max Range: 2.4749. Min Range: -2.4749

Max Act: 1.7925. Min Act: -0.0000

Data Index: 1551786 (Python Code)

Max Activating Token Index: 203

Text #4

Max Range: 2.4749. Min Range: -2.4749

Max Act: 2.3221. Min Act: -0.0000

Data Index: 1548651 (Python Code)

Max Activating Token Index: 307

Text #5

Max Range: 2.4749. Min Range: -2.4749

Max Act: 2.0552. Min Act: -0.0000

Data Index: 382063 (C4 (Web Text))

Max Activating Token Index: 968

Text #6

Max Range: 2.4749. Min Range: -2.4749

Max Act: 2.2424. Min Act: -0.0000

Data Index: 497121 (C4 (Web Text))

Max Activating Token Index: 653

Text #7

Max Range: 2.4749. Min Range: -2.4749

Max Act: 2.1196. Min Act: -0.0000

Data Index: 1579671 (Python Code)

Max Activating Token Index: 521

Text #8

Max Range: 2.4749. Min Range: -2.4749

Max Act: 2.1977. Min Act: -0.0000

Data Index: 1543989 (Python Code)

Max Activating Token Index: 758

Text #9

Max Range: 2.4749. Min Range: -2.4749

Max Act: 1.8481. Min Act: -0.0000

Data Index: 1165784 (C4 (Web Text))

Max Activating Token Index: 717

Text #10

Max Range: 2.4749. Min Range: -2.4749

Max Act: 2.0580. Min Act: -0.0000

Data Index: 596711 (C4 (Web Text))

Max Activating Token Index: 748

Text #11

Max Range: 2.4749. Min Range: -2.4749

Max Act: 1.9761. Min Act: -0.0000

Data Index: 1020963 (C4 (Web Text))

Max Activating Token Index: 621

Text #12

Max Range: 2.4749. Min Range: -2.4749

Max Act: 1.9132. Min Act: -0.0000

Data Index: 52298 (C4 (Web Text))

Max Activating Token Index: 755

Text #13

Max Range: 2.4749. Min Range: -2.4749

Max Act: 1.8879. Min Act: -0.0000

Data Index: 1426866 (Python Code)

Max Activating Token Index: 535

Text #14

Max Range: 2.4749. Min Range: -2.4749

Max Act: 1.8322. Min Act: -0.0000

Data Index: 514574 (C4 (Web Text))

Max Activating Token Index: 587

Text #15

Max Range: 2.4749. Min Range: -2.4749

Max Act: 1.7245. Min Act: -0.0000

Data Index: 1035003 (C4 (Web Text))

Max Activating Token Index: 859

Text #16

Max Range: 2.4749. Min Range: -2.4749

Max Act: 1.7304. Min Act: -0.0000

Data Index: 973526 (C4 (Web Text))

Max Activating Token Index: 680

Text #17

Max Range: 2.4749. Min Range: -2.4749

Max Act: 1.8186. Min Act: -0.0000

Data Index: 1291743 (C4 (Web Text))

Max Activating Token Index: 504

Text #18

Max Range: 2.4749. Min Range: -2.4749

Max Act: 1.7241. Min Act: -0.0000

Data Index: 130366 (C4 (Web Text))

Max Activating Token Index: 987

Text #19

Max Range: 2.4749. Min Range: -2.4749

Max Act: 1.6147. Min Act: -0.0000

Data Index: 1381252 (Python Code)

Max Activating Token Index: 202