Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2691 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.4488. Min Range: -2.4488

Max Act: 2.4488. Min Act: -0.0000

Data Index: 1505759 (Python Code)

Max Activating Token Index: 148

Text #1

Max Range: 2.4488. Min Range: -2.4488

Max Act: 2.4017. Min Act: -0.0000

Data Index: 1513154 (Python Code)

Max Activating Token Index: 587

Text #2

Max Range: 2.4488. Min Range: -2.4488

Max Act: 2.1653. Min Act: -0.0000

Data Index: 1594568 (Python Code)

Max Activating Token Index: 438

Text #3

Max Range: 2.4488. Min Range: -2.4488

Max Act: 2.0717. Min Act: -0.0000

Data Index: 1543278 (Python Code)

Max Activating Token Index: 225

Text #4

Max Range: 2.4488. Min Range: -2.4488

Max Act: 1.8444. Min Act: -0.0000

Data Index: 1581416 (Python Code)

Max Activating Token Index: 470

Text #5

Max Range: 2.4488. Min Range: -2.4488

Max Act: 1.9051. Min Act: -0.0000

Data Index: 1586887 (Python Code)

Max Activating Token Index: 130

Text #6

Max Range: 2.4488. Min Range: -2.4488

Max Act: 1.7275. Min Act: -0.0000

Data Index: 1450764 (Python Code)

Max Activating Token Index: 222

Text #7

Max Range: 2.4488. Min Range: -2.4488

Max Act: 1.8175. Min Act: -0.0000

Data Index: 1426477 (Python Code)

Max Activating Token Index: 572

Text #8

Max Range: 2.4488. Min Range: -2.4488

Max Act: 1.4008. Min Act: -0.0000

Data Index: 1371844 (Python Code)

Max Activating Token Index: 872

Text #9

Max Range: 2.4488. Min Range: -2.4488

Max Act: 1.7884. Min Act: -0.0000

Data Index: 1360728 (Python Code)

Max Activating Token Index: 514

Text #10

Max Range: 2.4488. Min Range: -2.4488

Max Act: 1.8041. Min Act: -0.0000

Data Index: 1464856 (Python Code)

Max Activating Token Index: 156

Text #11

Max Range: 2.4488. Min Range: -2.4488

Max Act: 1.6457. Min Act: -0.0000

Data Index: 1372538 (Python Code)

Max Activating Token Index: 607

Text #12

Max Range: 2.4488. Min Range: -2.4488

Max Act: 1.8284. Min Act: -0.0000

Data Index: 1607571 (Python Code)

Max Activating Token Index: 705

Text #13

Max Range: 2.4488. Min Range: -2.4488

Max Act: 1.5946. Min Act: -0.0000

Data Index: 1590823 (Python Code)

Max Activating Token Index: 23

Text #14

Max Range: 2.4488. Min Range: -2.4488

Max Act: 1.2710. Min Act: -0.0000

Data Index: 1361959 (Python Code)

Max Activating Token Index: 347

Text #15

Max Range: 2.4488. Min Range: -2.4488

Max Act: 1.5732. Min Act: -0.0000

Data Index: 1631491 (Python Code)

Max Activating Token Index: 8

Text #16

Max Range: 2.4488. Min Range: -2.4488

Max Act: 1.4690. Min Act: -0.0000

Data Index: 432461 (C4 (Web Text))

Max Activating Token Index: 519

Text #17

Max Range: 2.4488. Min Range: -2.4488

Max Act: 1.6222. Min Act: -0.0000

Data Index: 1636455 (Python Code)

Max Activating Token Index: 681

Text #18

Max Range: 2.4488. Min Range: -2.4488

Max Act: 1.4137. Min Act: -0.0000

Data Index: 1426833 (Python Code)

Max Activating Token Index: 17

Text #19

Max Range: 2.4488. Min Range: -2.4488

Max Act: 1.5000. Min Act: 0.0000

Data Index: 1395417 (Python Code)

Max Activating Token Index: 37