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

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

Neuron 2888 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8866. Min Range: -0.8866

Max Act: 0.8866. Min Act: -0.0000

Data Index: 1351412 (C4 (Web Text))

Max Activating Token Index: 629

Text #1

Max Range: 0.8866. Min Range: -0.8866

Max Act: 0.4436. Min Act: -0.0000

Data Index: 235985 (C4 (Web Text))

Max Activating Token Index: 620

Text #2

Max Range: 0.8866. Min Range: -0.8866

Max Act: 0.4030. Min Act: -0.0000

Data Index: 1079480 (C4 (Web Text))

Max Activating Token Index: 811

Text #3

Max Range: 0.8866. Min Range: -0.8866

Max Act: 0.3804. Min Act: -0.0000

Data Index: 403115 (C4 (Web Text))

Max Activating Token Index: 808

Text #4

Max Range: 0.8866. Min Range: -0.8866

Max Act: 0.3958. Min Act: -0.0000

Data Index: 93172 (C4 (Web Text))

Max Activating Token Index: 844

Text #5

Max Range: 0.8866. Min Range: -0.8866

Max Act: 0.4084. Min Act: -0.0000

Data Index: 1569710 (Python Code)

Max Activating Token Index: 717

Text #6

Max Range: 0.8866. Min Range: -0.8866

Max Act: 0.3939. Min Act: -0.0000

Data Index: 1404981 (Python Code)

Max Activating Token Index: 355

Text #7

Max Range: 0.8866. Min Range: -0.8866

Max Act: 0.3966. Min Act: -0.0000

Data Index: 1107921 (C4 (Web Text))

Max Activating Token Index: 927

Text #8

Max Range: 0.8866. Min Range: -0.8866

Max Act: 0.3340. Min Act: -0.0000

Data Index: 1564160 (Python Code)

Max Activating Token Index: 310

Text #9

Max Range: 0.8866. Min Range: -0.8866

Max Act: 0.3308. Min Act: -0.0000

Data Index: 1561611 (Python Code)

Max Activating Token Index: 902

Text #10

Max Range: 0.8866. Min Range: -0.8866

Max Act: 0.3145. Min Act: -0.0000

Data Index: 824970 (C4 (Web Text))

Max Activating Token Index: 905

Text #11

Max Range: 0.8866. Min Range: -0.8866

Max Act: 0.3255. Min Act: -0.0000

Data Index: 444237 (C4 (Web Text))

Max Activating Token Index: 1020

Text #12

Max Range: 0.8866. Min Range: -0.8866

Max Act: 0.3219. Min Act: -0.0000

Data Index: 1534633 (Python Code)

Max Activating Token Index: 996

Text #13

Max Range: 0.8866. Min Range: -0.8866

Max Act: 0.3206. Min Act: -0.0000

Data Index: 242674 (C4 (Web Text))

Max Activating Token Index: 516

Text #14

Max Range: 0.8866. Min Range: -0.8866

Max Act: 0.3164. Min Act: -0.0000

Data Index: 441431 (C4 (Web Text))

Max Activating Token Index: 213

Text #15

Max Range: 0.8866. Min Range: -0.8866

Max Act: 0.3307. Min Act: -0.0000

Data Index: 1593080 (Python Code)

Max Activating Token Index: 487

Text #16

Max Range: 0.8866. Min Range: -0.8866

Max Act: 0.3239. Min Act: -0.0000

Data Index: 503052 (C4 (Web Text))

Max Activating Token Index: 201

Text #17

Max Range: 0.8866. Min Range: -0.8866

Max Act: 0.3102. Min Act: -0.0000

Data Index: 1412872 (Python Code)

Max Activating Token Index: 530

Text #18

Max Range: 0.8866. Min Range: -0.8866

Max Act: 0.3491. Min Act: -0.0000

Data Index: 877222 (C4 (Web Text))

Max Activating Token Index: 347

Text #19

Max Range: 0.8866. Min Range: -0.8866

Max Act: 0.3089. Min Act: -0.0000

Data Index: 137562 (C4 (Web Text))

Max Activating Token Index: 370