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

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

Neuron 1061 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5941. Min Range: -1.5941

Max Act: 1.5941. Min Act: -0.0001

Data Index: 1199899 (C4 (Web Text))

Max Activating Token Index: 10

Text #1

Max Range: 1.5941. Min Range: -1.5941

Max Act: 1.4197. Min Act: -0.0001

Data Index: 1583856 (Python Code)

Max Activating Token Index: 579

Text #2

Max Range: 1.5941. Min Range: -1.5941

Max Act: 1.3799. Min Act: -0.0001

Data Index: 168431 (C4 (Web Text))

Max Activating Token Index: 416

Text #3

Max Range: 1.5941. Min Range: -1.5941

Max Act: 1.4155. Min Act: -0.0001

Data Index: 1456126 (Python Code)

Max Activating Token Index: 233

Text #4

Max Range: 1.5941. Min Range: -1.5941

Max Act: 1.4056. Min Act: -0.0001

Data Index: 613776 (C4 (Web Text))

Max Activating Token Index: 65

Text #5

Max Range: 1.5941. Min Range: -1.5941

Max Act: 1.3037. Min Act: -0.0001

Data Index: 572281 (C4 (Web Text))

Max Activating Token Index: 408

Text #6

Max Range: 1.5941. Min Range: -1.5941

Max Act: 1.3125. Min Act: -0.0001

Data Index: 842939 (C4 (Web Text))

Max Activating Token Index: 142

Text #7

Max Range: 1.5941. Min Range: -1.5941

Max Act: 1.3565. Min Act: -0.0001

Data Index: 1078882 (C4 (Web Text))

Max Activating Token Index: 833

Text #8

Max Range: 1.5941. Min Range: -1.5941

Max Act: 1.3360. Min Act: -0.0001

Data Index: 989103 (C4 (Web Text))

Max Activating Token Index: 606

Text #9

Max Range: 1.5941. Min Range: -1.5941

Max Act: 1.2702. Min Act: -0.0001

Data Index: 435914 (C4 (Web Text))

Max Activating Token Index: 489

Text #10

Max Range: 1.5941. Min Range: -1.5941

Max Act: 1.2308. Min Act: -0.0001

Data Index: 899239 (C4 (Web Text))

Max Activating Token Index: 493

Text #11

Max Range: 1.5941. Min Range: -1.5941

Max Act: 1.2561. Min Act: -0.0001

Data Index: 1208076 (C4 (Web Text))

Max Activating Token Index: 208

Text #12

Max Range: 1.5941. Min Range: -1.5941

Max Act: 1.2463. Min Act: -0.0001

Data Index: 221871 (C4 (Web Text))

Max Activating Token Index: 20

Text #13

Max Range: 1.5941. Min Range: -1.5941

Max Act: 1.1815. Min Act: -0.0001

Data Index: 1045579 (C4 (Web Text))

Max Activating Token Index: 488

Text #14

Max Range: 1.5941. Min Range: -1.5941

Max Act: 1.3026. Min Act: -0.0001

Data Index: 928243 (C4 (Web Text))

Max Activating Token Index: 694

Text #15

Max Range: 1.5941. Min Range: -1.5941

Max Act: 1.0013. Min Act: -0.0001

Data Index: 1174806 (C4 (Web Text))

Max Activating Token Index: 185

Text #16

Max Range: 1.5941. Min Range: -1.5941

Max Act: 1.1374. Min Act: -0.0001

Data Index: 832385 (C4 (Web Text))

Max Activating Token Index: 704

Text #17

Max Range: 1.5941. Min Range: -1.5941

Max Act: 1.1624. Min Act: -0.0001

Data Index: 1504204 (Python Code)

Max Activating Token Index: 326

Text #18

Max Range: 1.5941. Min Range: -1.5941

Max Act: 1.1339. Min Act: -0.0001

Data Index: 388414 (C4 (Web Text))

Max Activating Token Index: 990

Text #19

Max Range: 1.5941. Min Range: -1.5941

Max Act: 1.0682. Min Act: -0.0001

Data Index: 213913 (C4 (Web Text))

Max Activating Token Index: 82