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

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

Neuron 5600 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0609. Min Range: -1.0609

Max Act: 1.0609. Min Act: -0.0001

Data Index: 1137636 (C4 (Web Text))

Max Activating Token Index: 965

Text #1

Max Range: 1.0609. Min Range: -1.0609

Max Act: 0.8869. Min Act: -0.0001

Data Index: 1063679 (C4 (Web Text))

Max Activating Token Index: 146

Text #2

Max Range: 1.0609. Min Range: -1.0609

Max Act: 0.8900. Min Act: -0.0001

Data Index: 776168 (C4 (Web Text))

Max Activating Token Index: 376

Text #3

Max Range: 1.0609. Min Range: -1.0609

Max Act: 0.8163. Min Act: -0.0000

Data Index: 1374791 (Python Code)

Max Activating Token Index: 73

Text #4

Max Range: 1.0609. Min Range: -1.0609

Max Act: 0.8663. Min Act: -0.0000

Data Index: 236404 (C4 (Web Text))

Max Activating Token Index: 910

Text #5

Max Range: 1.0609. Min Range: -1.0609

Max Act: 0.7991. Min Act: -0.0000

Data Index: 1067012 (C4 (Web Text))

Max Activating Token Index: 465

Text #6

Max Range: 1.0609. Min Range: -1.0609

Max Act: 0.8133. Min Act: -0.0000

Data Index: 128505 (C4 (Web Text))

Max Activating Token Index: 115

Text #7

Max Range: 1.0609. Min Range: -1.0609

Max Act: 0.8139. Min Act: -0.0001

Data Index: 1083635 (C4 (Web Text))

Max Activating Token Index: 357

Text #8

Max Range: 1.0609. Min Range: -1.0609

Max Act: 0.8149. Min Act: -0.0001

Data Index: 871987 (C4 (Web Text))

Max Activating Token Index: 794

Text #9

Max Range: 1.0609. Min Range: -1.0609

Max Act: 0.7815. Min Act: -0.0001

Data Index: 329972 (C4 (Web Text))

Max Activating Token Index: 303

Text #10

Max Range: 1.0609. Min Range: -1.0609

Max Act: 0.7925. Min Act: -0.0001

Data Index: 541007 (C4 (Web Text))

Max Activating Token Index: 918

Text #11

Max Range: 1.0609. Min Range: -1.0609

Max Act: 0.7846. Min Act: -0.0000

Data Index: 798057 (C4 (Web Text))

Max Activating Token Index: 483

Text #12

Max Range: 1.0609. Min Range: -1.0609

Max Act: 0.7414. Min Act: -0.0000

Data Index: 172498 (C4 (Web Text))

Max Activating Token Index: 745

Text #13

Max Range: 1.0609. Min Range: -1.0609

Max Act: 0.7598. Min Act: -0.0000

Data Index: 1066344 (C4 (Web Text))

Max Activating Token Index: 161

Text #14

Max Range: 1.0609. Min Range: -1.0609

Max Act: 0.7343. Min Act: -0.0001

Data Index: 160159 (C4 (Web Text))

Max Activating Token Index: 402

Text #15

Max Range: 1.0609. Min Range: -1.0609

Max Act: 0.7541. Min Act: -0.0001

Data Index: 484179 (C4 (Web Text))

Max Activating Token Index: 601

Text #16

Max Range: 1.0609. Min Range: -1.0609

Max Act: 0.7330. Min Act: -0.0000

Data Index: 860074 (C4 (Web Text))

Max Activating Token Index: 312

Text #17

Max Range: 1.0609. Min Range: -1.0609

Max Act: 0.7101. Min Act: -0.0001

Data Index: 257548 (C4 (Web Text))

Max Activating Token Index: 192

Text #18

Max Range: 1.0609. Min Range: -1.0609

Max Act: 0.7528. Min Act: -0.0001

Data Index: 590442 (C4 (Web Text))

Max Activating Token Index: 550

Text #19

Max Range: 1.0609. Min Range: -1.0609

Max Act: 0.7433. Min Act: -0.0000

Data Index: 1121201 (C4 (Web Text))

Max Activating Token Index: 113