Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2528 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.6787. Min Range: -1.6787

Max Act: 1.6142. Min Act: -0.0000

Data Index: 355669 (C4 (Web Text))

Max Activating Token Index: 413

Text #1

Max Range: 1.6787. Min Range: -1.6787

Max Act: 1.6787. Min Act: -0.0000

Data Index: 1209611 (C4 (Web Text))

Max Activating Token Index: 300

Text #2

Max Range: 1.6787. Min Range: -1.6787

Max Act: 1.4280. Min Act: -0.0000

Data Index: 630112 (C4 (Web Text))

Max Activating Token Index: 334

Text #3

Max Range: 1.6787. Min Range: -1.6787

Max Act: 1.3869. Min Act: 0.0000

Data Index: 1617701 (Python Code)

Max Activating Token Index: 535

Text #4

Max Range: 1.6787. Min Range: -1.6787

Max Act: 1.3779. Min Act: -0.0000

Data Index: 121067 (C4 (Web Text))

Max Activating Token Index: 219

Text #5

Max Range: 1.6787. Min Range: -1.6787

Max Act: 1.2968. Min Act: -0.0000

Data Index: 993028 (C4 (Web Text))

Max Activating Token Index: 732

Text #6

Max Range: 1.6787. Min Range: -1.6787

Max Act: 1.1851. Min Act: -0.0000

Data Index: 960203 (C4 (Web Text))

Max Activating Token Index: 453

Text #7

Max Range: 1.6787. Min Range: -1.6787

Max Act: 1.0931. Min Act: -0.0000

Data Index: 538333 (C4 (Web Text))

Max Activating Token Index: 179

Text #8

Max Range: 1.6787. Min Range: -1.6787

Max Act: 1.1804. Min Act: 0.0000

Data Index: 760910 (C4 (Web Text))

Max Activating Token Index: 624

Text #9

Max Range: 1.6787. Min Range: -1.6787

Max Act: 1.1786. Min Act: -0.0000

Data Index: 876861 (C4 (Web Text))

Max Activating Token Index: 1022

Text #10

Max Range: 1.6787. Min Range: -1.6787

Max Act: 1.1496. Min Act: -0.0000

Data Index: 183851 (C4 (Web Text))

Max Activating Token Index: 869

Text #11

Max Range: 1.6787. Min Range: -1.6787

Max Act: 1.0280. Min Act: -0.0000

Data Index: 610405 (C4 (Web Text))

Max Activating Token Index: 684

Text #12

Max Range: 1.6787. Min Range: -1.6787

Max Act: 1.0641. Min Act: -0.0000

Data Index: 216037 (C4 (Web Text))

Max Activating Token Index: 453

Text #13

Max Range: 1.6787. Min Range: -1.6787

Max Act: 1.1168. Min Act: -0.0000

Data Index: 38407 (C4 (Web Text))

Max Activating Token Index: 1011

Text #14

Max Range: 1.6787. Min Range: -1.6787

Max Act: 1.0564. Min Act: -0.0000

Data Index: 1592121 (Python Code)

Max Activating Token Index: 887

Text #15

Max Range: 1.6787. Min Range: -1.6787

Max Act: 0.9959. Min Act: -0.0000

Data Index: 66972 (C4 (Web Text))

Max Activating Token Index: 503

Text #16

Max Range: 1.6787. Min Range: -1.6787

Max Act: 0.9660. Min Act: 0.0000

Data Index: 1315395 (C4 (Web Text))

Max Activating Token Index: 382

Text #17

Max Range: 1.6787. Min Range: -1.6787

Max Act: 0.9863. Min Act: -0.0000

Data Index: 384992 (C4 (Web Text))

Max Activating Token Index: 647

Text #18

Max Range: 1.6787. Min Range: -1.6787

Max Act: 0.9274. Min Act: 0.0000

Data Index: 365312 (C4 (Web Text))

Max Activating Token Index: 1020

Text #19

Max Range: 1.6787. Min Range: -1.6787

Max Act: 0.8618. Min Act: -0.0000

Data Index: 980578 (C4 (Web Text))

Max Activating Token Index: 859