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

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

Neuron 4064 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.8824. Min Range: -1.8824

Max Act: 1.8824. Min Act: -0.0001

Data Index: 764615 (C4 (Web Text))

Max Activating Token Index: 335

Text #1

Max Range: 1.8824. Min Range: -1.8824

Max Act: 1.7767. Min Act: -0.0001

Data Index: 5669 (C4 (Web Text))

Max Activating Token Index: 41

Text #2

Max Range: 1.8824. Min Range: -1.8824

Max Act: 1.7104. Min Act: -0.0001

Data Index: 27411 (C4 (Web Text))

Max Activating Token Index: 765

Text #3

Max Range: 1.8824. Min Range: -1.8824

Max Act: 1.7487. Min Act: -0.0001

Data Index: 926248 (C4 (Web Text))

Max Activating Token Index: 42

Text #4

Max Range: 1.8824. Min Range: -1.8824

Max Act: 1.7025. Min Act: -0.0001

Data Index: 552961 (C4 (Web Text))

Max Activating Token Index: 93

Text #5

Max Range: 1.8824. Min Range: -1.8824

Max Act: 1.7347. Min Act: -0.0001

Data Index: 332338 (C4 (Web Text))

Max Activating Token Index: 270

Text #6

Max Range: 1.8824. Min Range: -1.8824

Max Act: 1.6279. Min Act: -0.0001

Data Index: 1148686 (C4 (Web Text))

Max Activating Token Index: 508

Text #7

Max Range: 1.8824. Min Range: -1.8824

Max Act: 1.6175. Min Act: -0.0001

Data Index: 424010 (C4 (Web Text))

Max Activating Token Index: 87

Text #8

Max Range: 1.8824. Min Range: -1.8824

Max Act: 1.6389. Min Act: -0.0001

Data Index: 442299 (C4 (Web Text))

Max Activating Token Index: 860

Text #9

Max Range: 1.8824. Min Range: -1.8824

Max Act: 1.5559. Min Act: -0.0001

Data Index: 790666 (C4 (Web Text))

Max Activating Token Index: 32

Text #10

Max Range: 1.8824. Min Range: -1.8824

Max Act: 1.6250. Min Act: -0.0001

Data Index: 55553 (C4 (Web Text))

Max Activating Token Index: 293

Text #11

Max Range: 1.8824. Min Range: -1.8824

Max Act: 1.4983. Min Act: -0.0001

Data Index: 483900 (C4 (Web Text))

Max Activating Token Index: 286

Text #12

Max Range: 1.8824. Min Range: -1.8824

Max Act: 1.5598. Min Act: -0.0001

Data Index: 479222 (C4 (Web Text))

Max Activating Token Index: 586

Text #13

Max Range: 1.8824. Min Range: -1.8824

Max Act: 1.5699. Min Act: -0.0001

Data Index: 1101342 (C4 (Web Text))

Max Activating Token Index: 365

Text #14

Max Range: 1.8824. Min Range: -1.8824

Max Act: 1.4217. Min Act: -0.0001

Data Index: 1213461 (C4 (Web Text))

Max Activating Token Index: 787

Text #15

Max Range: 1.8824. Min Range: -1.8824

Max Act: 1.4650. Min Act: -0.0001

Data Index: 684338 (C4 (Web Text))

Max Activating Token Index: 474

Text #16

Max Range: 1.8824. Min Range: -1.8824

Max Act: 1.4370. Min Act: -0.0001

Data Index: 1287760 (C4 (Web Text))

Max Activating Token Index: 233

Text #17

Max Range: 1.8824. Min Range: -1.8824

Max Act: 1.4163. Min Act: -0.0001

Data Index: 453386 (C4 (Web Text))

Max Activating Token Index: 942

Text #18

Max Range: 1.8824. Min Range: -1.8824

Max Act: 1.4605. Min Act: -0.0001

Data Index: 374531 (C4 (Web Text))

Max Activating Token Index: 968

Text #19

Max Range: 1.8824. Min Range: -1.8824

Max Act: 1.4586. Min Act: -0.0001

Data Index: 266246 (C4 (Web Text))

Max Activating Token Index: 608