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

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

Neuron 2051 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8237. Min Range: -1.8237

Max Act: 1.8237. Min Act: -0.0001

Data Index: 1148971 (C4 (Web Text))

Max Activating Token Index: 486

Text #1

Max Range: 1.8237. Min Range: -1.8237

Max Act: 1.7624. Min Act: -0.0001

Data Index: 987513 (C4 (Web Text))

Max Activating Token Index: 89

Text #2

Max Range: 1.8237. Min Range: -1.8237

Max Act: 1.7530. Min Act: -0.0001

Data Index: 978142 (C4 (Web Text))

Max Activating Token Index: 971

Text #3

Max Range: 1.8237. Min Range: -1.8237

Max Act: 1.6240. Min Act: -0.0001

Data Index: 471696 (C4 (Web Text))

Max Activating Token Index: 669

Text #4

Max Range: 1.8237. Min Range: -1.8237

Max Act: 1.7211. Min Act: -0.0001

Data Index: 754334 (C4 (Web Text))

Max Activating Token Index: 651

Text #5

Max Range: 1.8237. Min Range: -1.8237

Max Act: 1.6449. Min Act: -0.0001

Data Index: 1343996 (C4 (Web Text))

Max Activating Token Index: 651

Text #6

Max Range: 1.8237. Min Range: -1.8237

Max Act: 1.6288. Min Act: -0.0001

Data Index: 1078727 (C4 (Web Text))

Max Activating Token Index: 298

Text #7

Max Range: 1.8237. Min Range: -1.8237

Max Act: 1.5537. Min Act: -0.0001

Data Index: 1349839 (C4 (Web Text))

Max Activating Token Index: 386

Text #8

Max Range: 1.8237. Min Range: -1.8237

Max Act: 1.7469. Min Act: -0.0001

Data Index: 873144 (C4 (Web Text))

Max Activating Token Index: 155

Text #9

Max Range: 1.8237. Min Range: -1.8237

Max Act: 1.6062. Min Act: -0.0001

Data Index: 631962 (C4 (Web Text))

Max Activating Token Index: 786

Text #10

Max Range: 1.8237. Min Range: -1.8237

Max Act: 1.6058. Min Act: -0.0001

Data Index: 1129787 (C4 (Web Text))

Max Activating Token Index: 228

Text #11

Max Range: 1.8237. Min Range: -1.8237

Max Act: 1.7042. Min Act: -0.0001

Data Index: 670908 (C4 (Web Text))

Max Activating Token Index: 721

Text #12

Max Range: 1.8237. Min Range: -1.8237

Max Act: 1.5623. Min Act: -0.0001

Data Index: 915447 (C4 (Web Text))

Max Activating Token Index: 215

Text #13

Max Range: 1.8237. Min Range: -1.8237

Max Act: 1.5945. Min Act: -0.0001

Data Index: 414043 (C4 (Web Text))

Max Activating Token Index: 748

Text #14

Max Range: 1.8237. Min Range: -1.8237

Max Act: 1.5197. Min Act: -0.0001

Data Index: 97874 (C4 (Web Text))

Max Activating Token Index: 23

Text #15

Max Range: 1.8237. Min Range: -1.8237

Max Act: 1.6560. Min Act: -0.0001

Data Index: 716700 (C4 (Web Text))

Max Activating Token Index: 399

Text #16

Max Range: 1.8237. Min Range: -1.8237

Max Act: 1.3875. Min Act: -0.0001

Data Index: 213725 (C4 (Web Text))

Max Activating Token Index: 146

Text #17

Max Range: 1.8237. Min Range: -1.8237

Max Act: 1.3832. Min Act: -0.0001

Data Index: 840021 (C4 (Web Text))

Max Activating Token Index: 234

Text #18

Max Range: 1.8237. Min Range: -1.8237

Max Act: 1.5064. Min Act: -0.0001

Data Index: 660775 (C4 (Web Text))

Max Activating Token Index: 674

Text #19

Max Range: 1.8237. Min Range: -1.8237

Max Act: 1.5379. Min Act: -0.0001

Data Index: 73082 (C4 (Web Text))

Max Activating Token Index: 822