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

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

Neuron 3095 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1556. Min Range: -1.1556

Max Act: 1.1556. Min Act: 0.0000

Data Index: 836793 (C4 (Web Text))

Max Activating Token Index: 14

Text #1

Max Range: 1.1556. Min Range: -1.1556

Max Act: 0.8533. Min Act: -0.0000

Data Index: 548127 (C4 (Web Text))

Max Activating Token Index: 493

Text #2

Max Range: 1.1556. Min Range: -1.1556

Max Act: 0.8039. Min Act: 0.0001

Data Index: 340658 (C4 (Web Text))

Max Activating Token Index: 606

Text #3

Max Range: 1.1556. Min Range: -1.1556

Max Act: 0.7317. Min Act: -0.0000

Data Index: 1062256 (C4 (Web Text))

Max Activating Token Index: 709

Text #4

Max Range: 1.1556. Min Range: -1.1556

Max Act: 0.7602. Min Act: -0.0000

Data Index: 1301583 (C4 (Web Text))

Max Activating Token Index: 188

Text #5

Max Range: 1.1556. Min Range: -1.1556

Max Act: 0.7569. Min Act: 0.0000

Data Index: 1054346 (C4 (Web Text))

Max Activating Token Index: 574

Text #6

Max Range: 1.1556. Min Range: -1.1556

Max Act: 0.7097. Min Act: -0.0000

Data Index: 1030692 (C4 (Web Text))

Max Activating Token Index: 263

Text #7

Max Range: 1.1556. Min Range: -1.1556

Max Act: 0.6887. Min Act: -0.0000

Data Index: 779543 (C4 (Web Text))

Max Activating Token Index: 547

Text #8

Max Range: 1.1556. Min Range: -1.1556

Max Act: 0.7131. Min Act: -0.0000

Data Index: 430420 (C4 (Web Text))

Max Activating Token Index: 535

Text #9

Max Range: 1.1556. Min Range: -1.1556

Max Act: 0.6466. Min Act: 0.0001

Data Index: 1107705 (C4 (Web Text))

Max Activating Token Index: 787

Text #10

Max Range: 1.1556. Min Range: -1.1556

Max Act: 0.6748. Min Act: -0.0000

Data Index: 1004905 (C4 (Web Text))

Max Activating Token Index: 904

Text #11

Max Range: 1.1556. Min Range: -1.1556

Max Act: 0.7143. Min Act: -0.0000

Data Index: 1209240 (C4 (Web Text))

Max Activating Token Index: 794

Text #12

Max Range: 1.1556. Min Range: -1.1556

Max Act: 0.6933. Min Act: -0.0000

Data Index: 344793 (C4 (Web Text))

Max Activating Token Index: 425

Text #13

Max Range: 1.1556. Min Range: -1.1556

Max Act: 0.6506. Min Act: -0.0000

Data Index: 1180175 (C4 (Web Text))

Max Activating Token Index: 242

Text #14

Max Range: 1.1556. Min Range: -1.1556

Max Act: 0.6693. Min Act: -0.0000

Data Index: 1481252 (Python Code)

Max Activating Token Index: 964

Text #15

Max Range: 1.1556. Min Range: -1.1556

Max Act: 0.6531. Min Act: -0.0000

Data Index: 96913 (C4 (Web Text))

Max Activating Token Index: 298

Text #16

Max Range: 1.1556. Min Range: -1.1556

Max Act: 0.6467. Min Act: -0.0000

Data Index: 1349893 (C4 (Web Text))

Max Activating Token Index: 210

Text #17

Max Range: 1.1556. Min Range: -1.1556

Max Act: 0.6427. Min Act: -0.0000

Data Index: 1072819 (C4 (Web Text))

Max Activating Token Index: 381

Text #18

Max Range: 1.1556. Min Range: -1.1556

Max Act: 0.6641. Min Act: -0.0000

Data Index: 259940 (C4 (Web Text))

Max Activating Token Index: 211

Text #19

Max Range: 1.1556. Min Range: -1.1556

Max Act: 0.6695. Min Act: -0.0000

Data Index: 1166986 (C4 (Web Text))

Max Activating Token Index: 185