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

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

Neuron 3048 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5544. Min Range: -1.5544

Max Act: 1.5396. Min Act: -0.0000

Data Index: 1240390 (C4 (Web Text))

Max Activating Token Index: 800

Text #1

Max Range: 1.5544. Min Range: -1.5544

Max Act: 1.5356. Min Act: -0.0000

Data Index: 895245 (C4 (Web Text))

Max Activating Token Index: 947

Text #2

Max Range: 1.5544. Min Range: -1.5544

Max Act: 1.5525. Min Act: -0.0000

Data Index: 549010 (C4 (Web Text))

Max Activating Token Index: 870

Text #3

Max Range: 1.5544. Min Range: -1.5544

Max Act: 1.3803. Min Act: -0.0000

Data Index: 1109417 (C4 (Web Text))

Max Activating Token Index: 957

Text #4

Max Range: 1.5544. Min Range: -1.5544

Max Act: 1.5544. Min Act: -0.0000

Data Index: 66465 (C4 (Web Text))

Max Activating Token Index: 249

Text #5

Max Range: 1.5544. Min Range: -1.5544

Max Act: 1.4395. Min Act: -0.0000

Data Index: 232172 (C4 (Web Text))

Max Activating Token Index: 21

Text #6

Max Range: 1.5544. Min Range: -1.5544

Max Act: 1.5280. Min Act: -0.0000

Data Index: 434431 (C4 (Web Text))

Max Activating Token Index: 1006

Text #7

Max Range: 1.5544. Min Range: -1.5544

Max Act: 1.3940. Min Act: -0.0000

Data Index: 1150682 (C4 (Web Text))

Max Activating Token Index: 825

Text #8

Max Range: 1.5544. Min Range: -1.5544

Max Act: 1.4206. Min Act: -0.0000

Data Index: 911217 (C4 (Web Text))

Max Activating Token Index: 774

Text #9

Max Range: 1.5544. Min Range: -1.5544

Max Act: 1.3800. Min Act: -0.0000

Data Index: 795949 (C4 (Web Text))

Max Activating Token Index: 528

Text #10

Max Range: 1.5544. Min Range: -1.5544

Max Act: 1.3991. Min Act: -0.0000

Data Index: 42691 (C4 (Web Text))

Max Activating Token Index: 434

Text #11

Max Range: 1.5544. Min Range: -1.5544

Max Act: 1.3423. Min Act: -0.0000

Data Index: 1143843 (C4 (Web Text))

Max Activating Token Index: 912

Text #12

Max Range: 1.5544. Min Range: -1.5544

Max Act: 1.3023. Min Act: -0.0000

Data Index: 591869 (C4 (Web Text))

Max Activating Token Index: 903

Text #13

Max Range: 1.5544. Min Range: -1.5544

Max Act: 1.1756. Min Act: -0.0000

Data Index: 954762 (C4 (Web Text))

Max Activating Token Index: 324

Text #14

Max Range: 1.5544. Min Range: -1.5544

Max Act: 1.3481. Min Act: -0.0000

Data Index: 1055408 (C4 (Web Text))

Max Activating Token Index: 333

Text #15

Max Range: 1.5544. Min Range: -1.5544

Max Act: 1.3432. Min Act: -0.0000

Data Index: 741542 (C4 (Web Text))

Max Activating Token Index: 323

Text #16

Max Range: 1.5544. Min Range: -1.5544

Max Act: 1.4093. Min Act: -0.0000

Data Index: 822154 (C4 (Web Text))

Max Activating Token Index: 428

Text #17

Max Range: 1.5544. Min Range: -1.5544

Max Act: 1.3548. Min Act: -0.0000

Data Index: 1299460 (C4 (Web Text))

Max Activating Token Index: 691

Text #18

Max Range: 1.5544. Min Range: -1.5544

Max Act: 1.3053. Min Act: -0.0000

Data Index: 660176 (C4 (Web Text))

Max Activating Token Index: 44

Text #19

Max Range: 1.5544. Min Range: -1.5544

Max Act: 1.2493. Min Act: -0.0000

Data Index: 1042334 (C4 (Web Text))

Max Activating Token Index: 263