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

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

Neuron 2010 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9026. Min Range: -0.9026

Max Act: 0.8586. Min Act: -0.0000

Data Index: 209523 (C4 (Web Text))

Max Activating Token Index: 975

Text #1

Max Range: 0.9026. Min Range: -0.9026

Max Act: 0.9026. Min Act: -0.0000

Data Index: 681180 (C4 (Web Text))

Max Activating Token Index: 811

Text #2

Max Range: 0.9026. Min Range: -0.9026

Max Act: 0.8826. Min Act: 0.0002

Data Index: 1495457 (Python Code)

Max Activating Token Index: 51

Text #3

Max Range: 0.9026. Min Range: -0.9026

Max Act: 0.8252. Min Act: -0.0000

Data Index: 381655 (C4 (Web Text))

Max Activating Token Index: 275

Text #4

Max Range: 0.9026. Min Range: -0.9026

Max Act: 0.8646. Min Act: -0.0000

Data Index: 189290 (C4 (Web Text))

Max Activating Token Index: 404

Text #5

Max Range: 0.9026. Min Range: -0.9026

Max Act: 0.8576. Min Act: -0.0000

Data Index: 58045 (C4 (Web Text))

Max Activating Token Index: 693

Text #6

Max Range: 0.9026. Min Range: -0.9026

Max Act: 0.7965. Min Act: -0.0000

Data Index: 1560388 (Python Code)

Max Activating Token Index: 32

Text #7

Max Range: 0.9026. Min Range: -0.9026

Max Act: 0.8101. Min Act: -0.0000

Data Index: 443105 (C4 (Web Text))

Max Activating Token Index: 952

Text #8

Max Range: 0.9026. Min Range: -0.9026

Max Act: 0.8151. Min Act: -0.0000

Data Index: 1461672 (Python Code)

Max Activating Token Index: 17

Text #9

Max Range: 0.9026. Min Range: -0.9026

Max Act: 0.8408. Min Act: -0.0000

Data Index: 848507 (C4 (Web Text))

Max Activating Token Index: 386

Text #10

Max Range: 0.9026. Min Range: -0.9026

Max Act: 0.8365. Min Act: -0.0000

Data Index: 851024 (C4 (Web Text))

Max Activating Token Index: 932

Text #11

Max Range: 0.9026. Min Range: -0.9026

Max Act: 0.8345. Min Act: -0.0000

Data Index: 623841 (C4 (Web Text))

Max Activating Token Index: 469

Text #12

Max Range: 0.9026. Min Range: -0.9026

Max Act: 0.8763. Min Act: 0.0002

Data Index: 1398186 (Python Code)

Max Activating Token Index: 51

Text #13

Max Range: 0.9026. Min Range: -0.9026

Max Act: 0.7663. Min Act: -0.0000

Data Index: 940799 (C4 (Web Text))

Max Activating Token Index: 346

Text #14

Max Range: 0.9026. Min Range: -0.9026

Max Act: 0.8171. Min Act: -0.0000

Data Index: 196923 (C4 (Web Text))

Max Activating Token Index: 486

Text #15

Max Range: 0.9026. Min Range: -0.9026

Max Act: 0.8081. Min Act: -0.0000

Data Index: 157698 (C4 (Web Text))

Max Activating Token Index: 450

Text #16

Max Range: 0.9026. Min Range: -0.9026

Max Act: 0.8335. Min Act: -0.0000

Data Index: 1016065 (C4 (Web Text))

Max Activating Token Index: 729

Text #17

Max Range: 0.9026. Min Range: -0.9026

Max Act: 0.7916. Min Act: -0.0000

Data Index: 27057 (C4 (Web Text))

Max Activating Token Index: 805

Text #18

Max Range: 0.9026. Min Range: -0.9026

Max Act: 0.7739. Min Act: -0.0000

Data Index: 16986 (C4 (Web Text))

Max Activating Token Index: 853

Text #19

Max Range: 0.9026. Min Range: -0.9026

Max Act: 0.7732. Min Act: -0.0000

Data Index: 161828 (C4 (Web Text))

Max Activating Token Index: 530