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

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

Neuron 1061 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7643. Min Range: -0.7643

Max Act: 0.7466. Min Act: -0.0001

Data Index: 1497193 (Python Code)

Max Activating Token Index: 380

Text #1

Max Range: 0.7643. Min Range: -0.7643

Max Act: 0.7643. Min Act: -0.0000

Data Index: 1621964 (Python Code)

Max Activating Token Index: 609

Text #2

Max Range: 0.7643. Min Range: -0.7643

Max Act: 0.7191. Min Act: -0.0000

Data Index: 1440815 (Python Code)

Max Activating Token Index: 154

Text #3

Max Range: 0.7643. Min Range: -0.7643

Max Act: 0.6757. Min Act: -0.0001

Data Index: 51007 (C4 (Web Text))

Max Activating Token Index: 787

Text #4

Max Range: 0.7643. Min Range: -0.7643

Max Act: 0.6410. Min Act: -0.0001

Data Index: 1620565 (Python Code)

Max Activating Token Index: 360

Text #5

Max Range: 0.7643. Min Range: -0.7643

Max Act: 0.5049. Min Act: -0.0001

Data Index: 1119795 (C4 (Web Text))

Max Activating Token Index: 270

Text #6

Max Range: 0.7643. Min Range: -0.7643

Max Act: 0.6269. Min Act: -0.0001

Data Index: 1460357 (Python Code)

Max Activating Token Index: 1022

Text #7

Max Range: 0.7643. Min Range: -0.7643

Max Act: 0.6282. Min Act: -0.0001

Data Index: 1627134 (Python Code)

Max Activating Token Index: 175

Text #8

Max Range: 0.7643. Min Range: -0.7643

Max Act: 0.6465. Min Act: -0.0000

Data Index: 1585447 (Python Code)

Max Activating Token Index: 887

Text #9

Max Range: 0.7643. Min Range: -0.7643

Max Act: 0.5731. Min Act: -0.0001

Data Index: 1332534 (C4 (Web Text))

Max Activating Token Index: 742

Text #10

Max Range: 0.7643. Min Range: -0.7643

Max Act: 0.6211. Min Act: -0.0000

Data Index: 1312750 (C4 (Web Text))

Max Activating Token Index: 718

Text #11

Max Range: 0.7643. Min Range: -0.7643

Max Act: 0.6143. Min Act: -0.0000

Data Index: 1273162 (C4 (Web Text))

Max Activating Token Index: 224

Text #12

Max Range: 0.7643. Min Range: -0.7643

Max Act: 0.5755. Min Act: -0.0001

Data Index: 268835 (C4 (Web Text))

Max Activating Token Index: 486

Text #13

Max Range: 0.7643. Min Range: -0.7643

Max Act: 0.5722. Min Act: -0.0001

Data Index: 1583179 (Python Code)

Max Activating Token Index: 493

Text #14

Max Range: 0.7643. Min Range: -0.7643

Max Act: 0.5235. Min Act: -0.0000

Data Index: 1500450 (Python Code)

Max Activating Token Index: 255

Text #15

Max Range: 0.7643. Min Range: -0.7643

Max Act: 0.6000. Min Act: -0.0001

Data Index: 1231222 (C4 (Web Text))

Max Activating Token Index: 470

Text #16

Max Range: 0.7643. Min Range: -0.7643

Max Act: 0.5403. Min Act: -0.0000

Data Index: 369140 (C4 (Web Text))

Max Activating Token Index: 641

Text #17

Max Range: 0.7643. Min Range: -0.7643

Max Act: 0.5252. Min Act: -0.0001

Data Index: 832757 (C4 (Web Text))

Max Activating Token Index: 671

Text #18

Max Range: 0.7643. Min Range: -0.7643

Max Act: 0.5216. Min Act: -0.0001

Data Index: 312251 (C4 (Web Text))

Max Activating Token Index: 402

Text #19

Max Range: 0.7643. Min Range: -0.7643

Max Act: 0.5339. Min Act: -0.0000

Data Index: 586269 (C4 (Web Text))

Max Activating Token Index: 579