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

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

Neuron 4191 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: 0.5598. Min Range: -0.5598

Max Act: 0.5598. Min Act: 0.0000

Data Index: 810765 (C4 (Web Text))

Max Activating Token Index: 173

Text #1

Max Range: 0.5598. Min Range: -0.5598

Max Act: 0.5396. Min Act: -0.0000

Data Index: 505394 (C4 (Web Text))

Max Activating Token Index: 314

Text #2

Max Range: 0.5598. Min Range: -0.5598

Max Act: 0.5205. Min Act: -0.0000

Data Index: 1149226 (C4 (Web Text))

Max Activating Token Index: 741

Text #3

Max Range: 0.5598. Min Range: -0.5598

Max Act: 0.4815. Min Act: -0.0000

Data Index: 863618 (C4 (Web Text))

Max Activating Token Index: 820

Text #4

Max Range: 0.5598. Min Range: -0.5598

Max Act: 0.4961. Min Act: -0.0000

Data Index: 1106490 (C4 (Web Text))

Max Activating Token Index: 288

Text #5

Max Range: 0.5598. Min Range: -0.5598

Max Act: 0.4848. Min Act: -0.0000

Data Index: 149211 (C4 (Web Text))

Max Activating Token Index: 556

Text #6

Max Range: 0.5598. Min Range: -0.5598

Max Act: 0.4677. Min Act: -0.0000

Data Index: 728930 (C4 (Web Text))

Max Activating Token Index: 728

Text #7

Max Range: 0.5598. Min Range: -0.5598

Max Act: 0.4991. Min Act: -0.0000

Data Index: 186237 (C4 (Web Text))

Max Activating Token Index: 999

Text #8

Max Range: 0.5598. Min Range: -0.5598

Max Act: 0.4806. Min Act: -0.0000

Data Index: 1348654 (C4 (Web Text))

Max Activating Token Index: 920

Text #9

Max Range: 0.5598. Min Range: -0.5598

Max Act: 0.4532. Min Act: -0.0000

Data Index: 87845 (C4 (Web Text))

Max Activating Token Index: 364

Text #10

Max Range: 0.5598. Min Range: -0.5598

Max Act: 0.4191. Min Act: -0.0000

Data Index: 256252 (C4 (Web Text))

Max Activating Token Index: 636

Text #11

Max Range: 0.5598. Min Range: -0.5598

Max Act: 0.4758. Min Act: -0.0000

Data Index: 1333054 (C4 (Web Text))

Max Activating Token Index: 728

Text #12

Max Range: 0.5598. Min Range: -0.5598

Max Act: 0.4403. Min Act: -0.0000

Data Index: 471334 (C4 (Web Text))

Max Activating Token Index: 736

Text #13

Max Range: 0.5598. Min Range: -0.5598

Max Act: 0.4515. Min Act: -0.0000

Data Index: 179276 (C4 (Web Text))

Max Activating Token Index: 392

Text #14

Max Range: 0.5598. Min Range: -0.5598

Max Act: 0.4550. Min Act: -0.0000

Data Index: 1190074 (C4 (Web Text))

Max Activating Token Index: 583

Text #15

Max Range: 0.5598. Min Range: -0.5598

Max Act: 0.4774. Min Act: -0.0000

Data Index: 783837 (C4 (Web Text))

Max Activating Token Index: 999

Text #16

Max Range: 0.5598. Min Range: -0.5598

Max Act: 0.4321. Min Act: -0.0000

Data Index: 119687 (C4 (Web Text))

Max Activating Token Index: 32

Text #17

Max Range: 0.5598. Min Range: -0.5598

Max Act: 0.4568. Min Act: -0.0000

Data Index: 1044360 (C4 (Web Text))

Max Activating Token Index: 330

Text #18

Max Range: 0.5598. Min Range: -0.5598

Max Act: 0.4569. Min Act: -0.0000

Data Index: 205523 (C4 (Web Text))

Max Activating Token Index: 418

Text #19

Max Range: 0.5598. Min Range: -0.5598

Max Act: 0.4249. Min Act: -0.0000

Data Index: 15321 (C4 (Web Text))

Max Activating Token Index: 660