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

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

Neuron 520 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5273. Min Range: -1.5273

Max Act: 1.5273. Min Act: -0.0001

Data Index: 609465 (C4 (Web Text))

Max Activating Token Index: 41

Text #1

Max Range: 1.5273. Min Range: -1.5273

Max Act: 1.2935. Min Act: -0.0001

Data Index: 573782 (C4 (Web Text))

Max Activating Token Index: 357

Text #2

Max Range: 1.5273. Min Range: -1.5273

Max Act: 1.1820. Min Act: -0.0001

Data Index: 524985 (C4 (Web Text))

Max Activating Token Index: 202

Text #3

Max Range: 1.5273. Min Range: -1.5273

Max Act: 0.9937. Min Act: -0.0001

Data Index: 676613 (C4 (Web Text))

Max Activating Token Index: 256

Text #4

Max Range: 1.5273. Min Range: -1.5273

Max Act: 0.9237. Min Act: -0.0001

Data Index: 1296338 (C4 (Web Text))

Max Activating Token Index: 152

Text #5

Max Range: 1.5273. Min Range: -1.5273

Max Act: 0.8026. Min Act: -0.0001

Data Index: 1296329 (C4 (Web Text))

Max Activating Token Index: 306

Text #6

Max Range: 1.5273. Min Range: -1.5273

Max Act: 0.8144. Min Act: -0.0001

Data Index: 563015 (C4 (Web Text))

Max Activating Token Index: 364

Text #7

Max Range: 1.5273. Min Range: -1.5273

Max Act: 0.6934. Min Act: -0.0001

Data Index: 697283 (C4 (Web Text))

Max Activating Token Index: 233

Text #8

Max Range: 1.5273. Min Range: -1.5273

Max Act: 0.9459. Min Act: -0.0001

Data Index: 1197913 (C4 (Web Text))

Max Activating Token Index: 403

Text #9

Max Range: 1.5273. Min Range: -1.5273

Max Act: 0.8594. Min Act: -0.0001

Data Index: 836178 (C4 (Web Text))

Max Activating Token Index: 10

Text #10

Max Range: 1.5273. Min Range: -1.5273

Max Act: 0.8759. Min Act: -0.0001

Data Index: 718842 (C4 (Web Text))

Max Activating Token Index: 71

Text #11

Max Range: 1.5273. Min Range: -1.5273

Max Act: 0.8402. Min Act: -0.0001

Data Index: 175167 (C4 (Web Text))

Max Activating Token Index: 40

Text #12

Max Range: 1.5273. Min Range: -1.5273

Max Act: 0.8223. Min Act: -0.0001

Data Index: 1136167 (C4 (Web Text))

Max Activating Token Index: 949

Text #13

Max Range: 1.5273. Min Range: -1.5273

Max Act: 0.7609. Min Act: -0.0001

Data Index: 154434 (C4 (Web Text))

Max Activating Token Index: 486

Text #14

Max Range: 1.5273. Min Range: -1.5273

Max Act: 0.6985. Min Act: -0.0001

Data Index: 830110 (C4 (Web Text))

Max Activating Token Index: 130

Text #15

Max Range: 1.5273. Min Range: -1.5273

Max Act: 0.8070. Min Act: -0.0001

Data Index: 1112328 (C4 (Web Text))

Max Activating Token Index: 525

Text #16

Max Range: 1.5273. Min Range: -1.5273

Max Act: 0.7132. Min Act: -0.0001

Data Index: 722841 (C4 (Web Text))

Max Activating Token Index: 965

Text #17

Max Range: 1.5273. Min Range: -1.5273

Max Act: 0.7389. Min Act: -0.0001

Data Index: 925067 (C4 (Web Text))

Max Activating Token Index: 384

Text #18

Max Range: 1.5273. Min Range: -1.5273

Max Act: 0.7217. Min Act: -0.0001

Data Index: 441062 (C4 (Web Text))

Max Activating Token Index: 125

Text #19

Max Range: 1.5273. Min Range: -1.5273

Max Act: 0.7287. Min Act: -0.0001

Data Index: 33094 (C4 (Web Text))

Max Activating Token Index: 402