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

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

Neuron 4983 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 11.5729. Min Range: -11.5729

Max Act: 11.5729. Min Act: -0.0000

Data Index: 1188448 (C4 (Web Text))

Max Activating Token Index: 662

Text #1

Max Range: 11.5729. Min Range: -11.5729

Max Act: 9.6201. Min Act: -0.0000

Data Index: 1151174 (C4 (Web Text))

Max Activating Token Index: 305

Text #2

Max Range: 11.5729. Min Range: -11.5729

Max Act: 7.7776. Min Act: -0.0000

Data Index: 1113037 (C4 (Web Text))

Max Activating Token Index: 1002

Text #3

Max Range: 11.5729. Min Range: -11.5729

Max Act: 3.3895. Min Act: -0.0000

Data Index: 1333867 (C4 (Web Text))

Max Activating Token Index: 145

Text #4

Max Range: 11.5729. Min Range: -11.5729

Max Act: 2.7747. Min Act: -0.0000

Data Index: 1327536 (C4 (Web Text))

Max Activating Token Index: 317

Text #5

Max Range: 11.5729. Min Range: -11.5729

Max Act: 2.2018. Min Act: -0.0000

Data Index: 64404 (C4 (Web Text))

Max Activating Token Index: 484

Text #6

Max Range: 11.5729. Min Range: -11.5729

Max Act: 2.1880. Min Act: -0.0000

Data Index: 985884 (C4 (Web Text))

Max Activating Token Index: 800

Text #7

Max Range: 11.5729. Min Range: -11.5729

Max Act: 1.6643. Min Act: -0.0000

Data Index: 640755 (C4 (Web Text))

Max Activating Token Index: 189

Text #8

Max Range: 11.5729. Min Range: -11.5729

Max Act: 1.4065. Min Act: -0.0000

Data Index: 525320 (C4 (Web Text))

Max Activating Token Index: 271

Text #9

Max Range: 11.5729. Min Range: -11.5729

Max Act: 1.5608. Min Act: -0.0000

Data Index: 1267147 (C4 (Web Text))

Max Activating Token Index: 347

Text #10

Max Range: 11.5729. Min Range: -11.5729

Max Act: 1.2956. Min Act: -0.0001

Data Index: 1447546 (Python Code)

Max Activating Token Index: 972

Text #11

Max Range: 11.5729. Min Range: -11.5729

Max Act: 1.3483. Min Act: -0.0000

Data Index: 193621 (C4 (Web Text))

Max Activating Token Index: 474

Text #12

Max Range: 11.5729. Min Range: -11.5729

Max Act: 0.9724. Min Act: -0.0000

Data Index: 1334887 (C4 (Web Text))

Max Activating Token Index: 448

Text #13

Max Range: 11.5729. Min Range: -11.5729

Max Act: 1.0037. Min Act: -0.0000

Data Index: 200795 (C4 (Web Text))

Max Activating Token Index: 219

Text #14

Max Range: 11.5729. Min Range: -11.5729

Max Act: 1.0872. Min Act: -0.0000

Data Index: 38625 (C4 (Web Text))

Max Activating Token Index: 620

Text #15

Max Range: 11.5729. Min Range: -11.5729

Max Act: 1.0793. Min Act: -0.0000

Data Index: 1329056 (C4 (Web Text))

Max Activating Token Index: 186

Text #16

Max Range: 11.5729. Min Range: -11.5729

Max Act: 0.9787. Min Act: -0.0000

Data Index: 741544 (C4 (Web Text))

Max Activating Token Index: 442

Text #17

Max Range: 11.5729. Min Range: -11.5729

Max Act: 0.9693. Min Act: -0.0000

Data Index: 1503506 (Python Code)

Max Activating Token Index: 158

Text #18

Max Range: 11.5729. Min Range: -11.5729

Max Act: 1.1079. Min Act: -0.0000

Data Index: 1100508 (C4 (Web Text))

Max Activating Token Index: 523

Text #19

Max Range: 11.5729. Min Range: -11.5729

Max Act: 1.1628. Min Act: -0.0000

Data Index: 1470549 (Python Code)

Max Activating Token Index: 112