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

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

Neuron 1173 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3045. Min Range: -2.3045

Max Act: 2.3045. Min Act: -0.0000

Data Index: 200747 (C4 (Web Text))

Max Activating Token Index: 409

Text #1

Max Range: 2.3045. Min Range: -2.3045

Max Act: 2.2721. Min Act: -0.0000

Data Index: 525189 (C4 (Web Text))

Max Activating Token Index: 118

Text #2

Max Range: 2.3045. Min Range: -2.3045

Max Act: 2.2281. Min Act: -0.0001

Data Index: 920322 (C4 (Web Text))

Max Activating Token Index: 903

Text #3

Max Range: 2.3045. Min Range: -2.3045

Max Act: 2.0575. Min Act: -0.0000

Data Index: 1039957 (C4 (Web Text))

Max Activating Token Index: 927

Text #4

Max Range: 2.3045. Min Range: -2.3045

Max Act: 2.0468. Min Act: -0.0000

Data Index: 1349753 (C4 (Web Text))

Max Activating Token Index: 876

Text #5

Max Range: 2.3045. Min Range: -2.3045

Max Act: 2.0584. Min Act: -0.0000

Data Index: 798711 (C4 (Web Text))

Max Activating Token Index: 568

Text #6

Max Range: 2.3045. Min Range: -2.3045

Max Act: 2.0361. Min Act: -0.0000

Data Index: 840238 (C4 (Web Text))

Max Activating Token Index: 911

Text #7

Max Range: 2.3045. Min Range: -2.3045

Max Act: 1.8349. Min Act: -0.0000

Data Index: 1344209 (C4 (Web Text))

Max Activating Token Index: 337

Text #8

Max Range: 2.3045. Min Range: -2.3045

Max Act: 1.8823. Min Act: -0.0000

Data Index: 669008 (C4 (Web Text))

Max Activating Token Index: 761

Text #9

Max Range: 2.3045. Min Range: -2.3045

Max Act: 1.8486. Min Act: -0.0000

Data Index: 960352 (C4 (Web Text))

Max Activating Token Index: 182

Text #10

Max Range: 2.3045. Min Range: -2.3045

Max Act: 1.8380. Min Act: -0.0000

Data Index: 1324240 (C4 (Web Text))

Max Activating Token Index: 532

Text #11

Max Range: 2.3045. Min Range: -2.3045

Max Act: 1.7711. Min Act: -0.0000

Data Index: 607113 (C4 (Web Text))

Max Activating Token Index: 448

Text #12

Max Range: 2.3045. Min Range: -2.3045

Max Act: 1.7802. Min Act: -0.0000

Data Index: 666929 (C4 (Web Text))

Max Activating Token Index: 503

Text #13

Max Range: 2.3045. Min Range: -2.3045

Max Act: 1.9245. Min Act: -0.0000

Data Index: 47377 (C4 (Web Text))

Max Activating Token Index: 659

Text #14

Max Range: 2.3045. Min Range: -2.3045

Max Act: 1.5469. Min Act: -0.0000

Data Index: 914916 (C4 (Web Text))

Max Activating Token Index: 994

Text #15

Max Range: 2.3045. Min Range: -2.3045

Max Act: 1.7917. Min Act: -0.0000

Data Index: 993013 (C4 (Web Text))

Max Activating Token Index: 666

Text #16

Max Range: 2.3045. Min Range: -2.3045

Max Act: 1.6256. Min Act: -0.0000

Data Index: 461177 (C4 (Web Text))

Max Activating Token Index: 867

Text #17

Max Range: 2.3045. Min Range: -2.3045

Max Act: 1.6189. Min Act: -0.0000

Data Index: 1305987 (C4 (Web Text))

Max Activating Token Index: 572

Text #18

Max Range: 2.3045. Min Range: -2.3045

Max Act: 1.7039. Min Act: -0.0000

Data Index: 315556 (C4 (Web Text))

Max Activating Token Index: 260

Text #19

Max Range: 2.3045. Min Range: -2.3045

Max Act: 1.8368. Min Act: -0.0000

Data Index: 131363 (C4 (Web Text))

Max Activating Token Index: 873