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

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

Neuron 2549 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: 1.3552. Min Range: -1.3552

Max Act: 1.3552. Min Act: -0.0000

Data Index: 254870 (C4 (Web Text))

Max Activating Token Index: 345

Text #1

Max Range: 1.3552. Min Range: -1.3552

Max Act: 1.1480. Min Act: -0.0000

Data Index: 219668 (C4 (Web Text))

Max Activating Token Index: 144

Text #2

Max Range: 1.3552. Min Range: -1.3552

Max Act: 1.0636. Min Act: -0.0000

Data Index: 572424 (C4 (Web Text))

Max Activating Token Index: 850

Text #3

Max Range: 1.3552. Min Range: -1.3552

Max Act: 1.0332. Min Act: -0.0000

Data Index: 60913 (C4 (Web Text))

Max Activating Token Index: 23

Text #4

Max Range: 1.3552. Min Range: -1.3552

Max Act: 1.0266. Min Act: -0.0000

Data Index: 1258268 (C4 (Web Text))

Max Activating Token Index: 249

Text #5

Max Range: 1.3552. Min Range: -1.3552

Max Act: 0.9939. Min Act: -0.0000

Data Index: 702643 (C4 (Web Text))

Max Activating Token Index: 113

Text #6

Max Range: 1.3552. Min Range: -1.3552

Max Act: 0.9953. Min Act: -0.0000

Data Index: 576608 (C4 (Web Text))

Max Activating Token Index: 893

Text #7

Max Range: 1.3552. Min Range: -1.3552

Max Act: 0.9999. Min Act: -0.0000

Data Index: 194979 (C4 (Web Text))

Max Activating Token Index: 824

Text #8

Max Range: 1.3552. Min Range: -1.3552

Max Act: 0.9174. Min Act: -0.0000

Data Index: 203699 (C4 (Web Text))

Max Activating Token Index: 103

Text #9

Max Range: 1.3552. Min Range: -1.3552

Max Act: 1.0246. Min Act: -0.0000

Data Index: 1353899 (C4 (Web Text))

Max Activating Token Index: 452

Text #10

Max Range: 1.3552. Min Range: -1.3552

Max Act: 0.8238. Min Act: -0.0000

Data Index: 935788 (C4 (Web Text))

Max Activating Token Index: 310

Text #11

Max Range: 1.3552. Min Range: -1.3552

Max Act: 0.8705. Min Act: -0.0000

Data Index: 516102 (C4 (Web Text))

Max Activating Token Index: 117

Text #12

Max Range: 1.3552. Min Range: -1.3552

Max Act: 0.7809. Min Act: -0.0000

Data Index: 94917 (C4 (Web Text))

Max Activating Token Index: 797

Text #13

Max Range: 1.3552. Min Range: -1.3552

Max Act: 0.8227. Min Act: -0.0000

Data Index: 1158049 (C4 (Web Text))

Max Activating Token Index: 60

Text #14

Max Range: 1.3552. Min Range: -1.3552

Max Act: 0.7989. Min Act: -0.0000

Data Index: 823563 (C4 (Web Text))

Max Activating Token Index: 180

Text #15

Max Range: 1.3552. Min Range: -1.3552

Max Act: 0.7356. Min Act: -0.0000

Data Index: 678396 (C4 (Web Text))

Max Activating Token Index: 370

Text #16

Max Range: 1.3552. Min Range: -1.3552

Max Act: 0.6394. Min Act: -0.0000

Data Index: 480031 (C4 (Web Text))

Max Activating Token Index: 595

Text #17

Max Range: 1.3552. Min Range: -1.3552

Max Act: 0.6824. Min Act: -0.0000

Data Index: 938478 (C4 (Web Text))

Max Activating Token Index: 229

Text #18

Max Range: 1.3552. Min Range: -1.3552

Max Act: 0.6992. Min Act: -0.0000

Data Index: 1054095 (C4 (Web Text))

Max Activating Token Index: 410

Text #19

Max Range: 1.3552. Min Range: -1.3552

Max Act: 0.6937. Min Act: -0.0000

Data Index: 1231261 (C4 (Web Text))

Max Activating Token Index: 137