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

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

Neuron 3745 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1597. Min Range: -3.1597

Max Act: 3.1597. Min Act: -0.0000

Data Index: 68074 (C4 (Web Text))

Max Activating Token Index: 458

Text #1

Max Range: 3.1597. Min Range: -3.1597

Max Act: 3.0166. Min Act: -0.0000

Data Index: 1331933 (C4 (Web Text))

Max Activating Token Index: 489

Text #2

Max Range: 3.1597. Min Range: -3.1597

Max Act: 3.1529. Min Act: -0.0000

Data Index: 372765 (C4 (Web Text))

Max Activating Token Index: 372

Text #3

Max Range: 3.1597. Min Range: -3.1597

Max Act: 2.9616. Min Act: -0.0000

Data Index: 912216 (C4 (Web Text))

Max Activating Token Index: 179

Text #4

Max Range: 3.1597. Min Range: -3.1597

Max Act: 2.8375. Min Act: -0.0000

Data Index: 354842 (C4 (Web Text))

Max Activating Token Index: 839

Text #5

Max Range: 3.1597. Min Range: -3.1597

Max Act: 2.4813. Min Act: -0.0000

Data Index: 977131 (C4 (Web Text))

Max Activating Token Index: 704

Text #6

Max Range: 3.1597. Min Range: -3.1597

Max Act: 2.4755. Min Act: -0.0000

Data Index: 1011890 (C4 (Web Text))

Max Activating Token Index: 343

Text #7

Max Range: 3.1597. Min Range: -3.1597

Max Act: 2.5865. Min Act: -0.0000

Data Index: 472009 (C4 (Web Text))

Max Activating Token Index: 68

Text #8

Max Range: 3.1597. Min Range: -3.1597

Max Act: 2.4440. Min Act: -0.0000

Data Index: 916287 (C4 (Web Text))

Max Activating Token Index: 242

Text #9

Max Range: 3.1597. Min Range: -3.1597

Max Act: 2.3074. Min Act: -0.0000

Data Index: 951498 (C4 (Web Text))

Max Activating Token Index: 290

Text #10

Max Range: 3.1597. Min Range: -3.1597

Max Act: 2.3777. Min Act: -0.0000

Data Index: 428444 (C4 (Web Text))

Max Activating Token Index: 295

Text #11

Max Range: 3.1597. Min Range: -3.1597

Max Act: 2.2374. Min Act: -0.0000

Data Index: 1034079 (C4 (Web Text))

Max Activating Token Index: 585

Text #12

Max Range: 3.1597. Min Range: -3.1597

Max Act: 2.3588. Min Act: -0.0000

Data Index: 43350 (C4 (Web Text))

Max Activating Token Index: 149

Text #13

Max Range: 3.1597. Min Range: -3.1597

Max Act: 2.2114. Min Act: -0.0000

Data Index: 232858 (C4 (Web Text))

Max Activating Token Index: 747

Text #14

Max Range: 3.1597. Min Range: -3.1597

Max Act: 2.1516. Min Act: -0.0000

Data Index: 1299148 (C4 (Web Text))

Max Activating Token Index: 691

Text #15

Max Range: 3.1597. Min Range: -3.1597

Max Act: 2.3413. Min Act: -0.0000

Data Index: 1329173 (C4 (Web Text))

Max Activating Token Index: 840

Text #16

Max Range: 3.1597. Min Range: -3.1597

Max Act: 2.0775. Min Act: -0.0000

Data Index: 1208514 (C4 (Web Text))

Max Activating Token Index: 734

Text #17

Max Range: 3.1597. Min Range: -3.1597

Max Act: 2.2752. Min Act: -0.0000

Data Index: 265265 (C4 (Web Text))

Max Activating Token Index: 954

Text #18

Max Range: 3.1597. Min Range: -3.1597

Max Act: 2.0729. Min Act: -0.0000

Data Index: 19176 (C4 (Web Text))

Max Activating Token Index: 225

Text #19

Max Range: 3.1597. Min Range: -3.1597

Max Act: 2.1633. Min Act: -0.0000

Data Index: 1274217 (C4 (Web Text))

Max Activating Token Index: 858