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

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

Neuron 2407 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: 1.6222. Min Range: -1.6222

Max Act: 1.4513. Min Act: 0.0002

Data Index: 688892 (C4 (Web Text))

Max Activating Token Index: 441

Text #1

Max Range: 1.6222. Min Range: -1.6222

Max Act: 1.6222. Min Act: 0.0000

Data Index: 380817 (C4 (Web Text))

Max Activating Token Index: 652

Text #2

Max Range: 1.6222. Min Range: -1.6222

Max Act: 1.3514. Min Act: 0.0001

Data Index: 938753 (C4 (Web Text))

Max Activating Token Index: 181

Text #3

Max Range: 1.6222. Min Range: -1.6222

Max Act: 1.3714. Min Act: 0.0001

Data Index: 1037422 (C4 (Web Text))

Max Activating Token Index: 891

Text #4

Max Range: 1.6222. Min Range: -1.6222

Max Act: 1.4776. Min Act: -0.0000

Data Index: 1454729 (Python Code)

Max Activating Token Index: 368

Text #5

Max Range: 1.6222. Min Range: -1.6222

Max Act: 1.1602. Min Act: -0.0000

Data Index: 1626269 (Python Code)

Max Activating Token Index: 303

Text #6

Max Range: 1.6222. Min Range: -1.6222

Max Act: 1.0445. Min Act: -0.0000

Data Index: 1381658 (Python Code)

Max Activating Token Index: 281

Text #7

Max Range: 1.6222. Min Range: -1.6222

Max Act: 1.1164. Min Act: -0.0000

Data Index: 281368 (C4 (Web Text))

Max Activating Token Index: 675

Text #8

Max Range: 1.6222. Min Range: -1.6222

Max Act: 1.1890. Min Act: -0.0000

Data Index: 250919 (C4 (Web Text))

Max Activating Token Index: 41

Text #9

Max Range: 1.6222. Min Range: -1.6222

Max Act: 1.1956. Min Act: 0.0001

Data Index: 524788 (C4 (Web Text))

Max Activating Token Index: 226

Text #10

Max Range: 1.6222. Min Range: -1.6222

Max Act: 1.1428. Min Act: 0.0001

Data Index: 274904 (C4 (Web Text))

Max Activating Token Index: 335

Text #11

Max Range: 1.6222. Min Range: -1.6222

Max Act: 1.0948. Min Act: 0.0000

Data Index: 806554 (C4 (Web Text))

Max Activating Token Index: 759

Text #12

Max Range: 1.6222. Min Range: -1.6222

Max Act: 1.0591. Min Act: -0.0000

Data Index: 4783 (C4 (Web Text))

Max Activating Token Index: 136

Text #13

Max Range: 1.6222. Min Range: -1.6222

Max Act: 1.0160. Min Act: -0.0000

Data Index: 990692 (C4 (Web Text))

Max Activating Token Index: 54

Text #14

Max Range: 1.6222. Min Range: -1.6222

Max Act: 1.0429. Min Act: -0.0000

Data Index: 110145 (C4 (Web Text))

Max Activating Token Index: 172

Text #15

Max Range: 1.6222. Min Range: -1.6222

Max Act: 0.8885. Min Act: -0.0000

Data Index: 574212 (C4 (Web Text))

Max Activating Token Index: 880

Text #16

Max Range: 1.6222. Min Range: -1.6222

Max Act: 1.1661. Min Act: -0.0000

Data Index: 344714 (C4 (Web Text))

Max Activating Token Index: 483

Text #17

Max Range: 1.6222. Min Range: -1.6222

Max Act: 1.0542. Min Act: -0.0000

Data Index: 998424 (C4 (Web Text))

Max Activating Token Index: 312

Text #18

Max Range: 1.6222. Min Range: -1.6222

Max Act: 0.9900. Min Act: 0.0000

Data Index: 272608 (C4 (Web Text))

Max Activating Token Index: 563

Text #19

Max Range: 1.6222. Min Range: -1.6222

Max Act: 1.0081. Min Act: -0.0000

Data Index: 465060 (C4 (Web Text))

Max Activating Token Index: 720