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

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

Neuron 3344 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3297. Min Range: -2.3297

Max Act: 2.2969. Min Act: -0.0000

Data Index: 259764 (C4 (Web Text))

Max Activating Token Index: 423

Text #1

Max Range: 2.3297. Min Range: -2.3297

Max Act: 2.2099. Min Act: -0.0000

Data Index: 896557 (C4 (Web Text))

Max Activating Token Index: 637

Text #2

Max Range: 2.3297. Min Range: -2.3297

Max Act: 2.0741. Min Act: -0.0000

Data Index: 880422 (C4 (Web Text))

Max Activating Token Index: 583

Text #3

Max Range: 2.3297. Min Range: -2.3297

Max Act: 2.2846. Min Act: -0.0001

Data Index: 1179422 (C4 (Web Text))

Max Activating Token Index: 946

Text #4

Max Range: 2.3297. Min Range: -2.3297

Max Act: 2.0247. Min Act: -0.0000

Data Index: 1146911 (C4 (Web Text))

Max Activating Token Index: 100

Text #5

Max Range: 2.3297. Min Range: -2.3297

Max Act: 2.1255. Min Act: -0.0000

Data Index: 477063 (C4 (Web Text))

Max Activating Token Index: 268

Text #6

Max Range: 2.3297. Min Range: -2.3297

Max Act: 2.0283. Min Act: -0.0000

Data Index: 521372 (C4 (Web Text))

Max Activating Token Index: 582

Text #7

Max Range: 2.3297. Min Range: -2.3297

Max Act: 2.3297. Min Act: -0.0000

Data Index: 417308 (C4 (Web Text))

Max Activating Token Index: 638

Text #8

Max Range: 2.3297. Min Range: -2.3297

Max Act: 1.8863. Min Act: -0.0000

Data Index: 1090162 (C4 (Web Text))

Max Activating Token Index: 810

Text #9

Max Range: 2.3297. Min Range: -2.3297

Max Act: 1.9348. Min Act: -0.0000

Data Index: 906015 (C4 (Web Text))

Max Activating Token Index: 118

Text #10

Max Range: 2.3297. Min Range: -2.3297

Max Act: 1.8956. Min Act: -0.0000

Data Index: 101498 (C4 (Web Text))

Max Activating Token Index: 18

Text #11

Max Range: 2.3297. Min Range: -2.3297

Max Act: 1.8970. Min Act: -0.0000

Data Index: 92809 (C4 (Web Text))

Max Activating Token Index: 261

Text #12

Max Range: 2.3297. Min Range: -2.3297

Max Act: 1.8735. Min Act: -0.0001

Data Index: 730568 (C4 (Web Text))

Max Activating Token Index: 15

Text #13

Max Range: 2.3297. Min Range: -2.3297

Max Act: 1.8742. Min Act: -0.0001

Data Index: 157415 (C4 (Web Text))

Max Activating Token Index: 696

Text #14

Max Range: 2.3297. Min Range: -2.3297

Max Act: 1.8673. Min Act: -0.0001

Data Index: 1253586 (C4 (Web Text))

Max Activating Token Index: 268

Text #15

Max Range: 2.3297. Min Range: -2.3297

Max Act: 2.0839. Min Act: -0.0000

Data Index: 485690 (C4 (Web Text))

Max Activating Token Index: 901

Text #16

Max Range: 2.3297. Min Range: -2.3297

Max Act: 1.9783. Min Act: -0.0000

Data Index: 1259854 (C4 (Web Text))

Max Activating Token Index: 213

Text #17

Max Range: 2.3297. Min Range: -2.3297

Max Act: 1.9788. Min Act: -0.0000

Data Index: 840605 (C4 (Web Text))

Max Activating Token Index: 519

Text #18

Max Range: 2.3297. Min Range: -2.3297

Max Act: 1.8775. Min Act: -0.0000

Data Index: 1133858 (C4 (Web Text))

Max Activating Token Index: 287

Text #19

Max Range: 2.3297. Min Range: -2.3297

Max Act: 2.0823. Min Act: -0.0000

Data Index: 467030 (C4 (Web Text))

Max Activating Token Index: 280