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

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

Neuron 4599 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: 0.6592. Min Range: -0.6592

Max Act: 0.6592. Min Act: -0.0000

Data Index: 1191163 (C4 (Web Text))

Max Activating Token Index: 307

Text #1

Max Range: 0.6592. Min Range: -0.6592

Max Act: 0.5907. Min Act: -0.0000

Data Index: 1099737 (C4 (Web Text))

Max Activating Token Index: 871

Text #2

Max Range: 0.6592. Min Range: -0.6592

Max Act: 0.5555. Min Act: -0.0000

Data Index: 53145 (C4 (Web Text))

Max Activating Token Index: 639

Text #3

Max Range: 0.6592. Min Range: -0.6592

Max Act: 0.5914. Min Act: -0.0000

Data Index: 232098 (C4 (Web Text))

Max Activating Token Index: 681

Text #4

Max Range: 0.6592. Min Range: -0.6592

Max Act: 0.5503. Min Act: -0.0000

Data Index: 1147121 (C4 (Web Text))

Max Activating Token Index: 159

Text #5

Max Range: 0.6592. Min Range: -0.6592

Max Act: 0.5123. Min Act: -0.0000

Data Index: 510844 (C4 (Web Text))

Max Activating Token Index: 289

Text #6

Max Range: 0.6592. Min Range: -0.6592

Max Act: 0.5242. Min Act: -0.0000

Data Index: 1259937 (C4 (Web Text))

Max Activating Token Index: 235

Text #7

Max Range: 0.6592. Min Range: -0.6592

Max Act: 0.4998. Min Act: -0.0000

Data Index: 1127835 (C4 (Web Text))

Max Activating Token Index: 157

Text #8

Max Range: 0.6592. Min Range: -0.6592

Max Act: 0.5050. Min Act: -0.0000

Data Index: 1131779 (C4 (Web Text))

Max Activating Token Index: 1001

Text #9

Max Range: 0.6592. Min Range: -0.6592

Max Act: 0.4413. Min Act: -0.0000

Data Index: 1286024 (C4 (Web Text))

Max Activating Token Index: 831

Text #10

Max Range: 0.6592. Min Range: -0.6592

Max Act: 0.5017. Min Act: -0.0000

Data Index: 622037 (C4 (Web Text))

Max Activating Token Index: 443

Text #11

Max Range: 0.6592. Min Range: -0.6592

Max Act: 0.4960. Min Act: -0.0000

Data Index: 681244 (C4 (Web Text))

Max Activating Token Index: 21

Text #12

Max Range: 0.6592. Min Range: -0.6592

Max Act: 0.4641. Min Act: -0.0000

Data Index: 770272 (C4 (Web Text))

Max Activating Token Index: 265

Text #13

Max Range: 0.6592. Min Range: -0.6592

Max Act: 0.4778. Min Act: -0.0000

Data Index: 111346 (C4 (Web Text))

Max Activating Token Index: 377

Text #14

Max Range: 0.6592. Min Range: -0.6592

Max Act: 0.4775. Min Act: -0.0000

Data Index: 864679 (C4 (Web Text))

Max Activating Token Index: 296

Text #15

Max Range: 0.6592. Min Range: -0.6592

Max Act: 0.4902. Min Act: -0.0000

Data Index: 1168637 (C4 (Web Text))

Max Activating Token Index: 329

Text #16

Max Range: 0.6592. Min Range: -0.6592

Max Act: 0.4367. Min Act: -0.0000

Data Index: 986510 (C4 (Web Text))

Max Activating Token Index: 850

Text #17

Max Range: 0.6592. Min Range: -0.6592

Max Act: 0.4627. Min Act: -0.0000

Data Index: 1012668 (C4 (Web Text))

Max Activating Token Index: 1015

Text #18

Max Range: 0.6592. Min Range: -0.6592

Max Act: 0.4467. Min Act: -0.0000

Data Index: 494424 (C4 (Web Text))

Max Activating Token Index: 138

Text #19

Max Range: 0.6592. Min Range: -0.6592

Max Act: 0.4420. Min Act: -0.0000

Data Index: 359482 (C4 (Web Text))

Max Activating Token Index: 573