Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1129 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.5514. Min Range: -1.5514

Max Act: 1.5514. Min Act: -0.0001

Data Index: 304863 (C4 (Web Text))

Max Activating Token Index: 873

Text #1

Max Range: 1.5514. Min Range: -1.5514

Max Act: 1.5508. Min Act: -0.0001

Data Index: 3803 (C4 (Web Text))

Max Activating Token Index: 605

Text #2

Max Range: 1.5514. Min Range: -1.5514

Max Act: 1.2963. Min Act: -0.0001

Data Index: 919703 (C4 (Web Text))

Max Activating Token Index: 655

Text #3

Max Range: 1.5514. Min Range: -1.5514

Max Act: 1.3970. Min Act: -0.0000

Data Index: 25242 (C4 (Web Text))

Max Activating Token Index: 29

Text #4

Max Range: 1.5514. Min Range: -1.5514

Max Act: 1.2047. Min Act: -0.0001

Data Index: 928265 (C4 (Web Text))

Max Activating Token Index: 65

Text #5

Max Range: 1.5514. Min Range: -1.5514

Max Act: 1.3070. Min Act: -0.0000

Data Index: 54613 (C4 (Web Text))

Max Activating Token Index: 38

Text #6

Max Range: 1.5514. Min Range: -1.5514

Max Act: 1.2840. Min Act: -0.0001

Data Index: 812011 (C4 (Web Text))

Max Activating Token Index: 414

Text #7

Max Range: 1.5514. Min Range: -1.5514

Max Act: 1.2188. Min Act: -0.0001

Data Index: 1011898 (C4 (Web Text))

Max Activating Token Index: 821

Text #8

Max Range: 1.5514. Min Range: -1.5514

Max Act: 1.0814. Min Act: -0.0001

Data Index: 590702 (C4 (Web Text))

Max Activating Token Index: 694

Text #9

Max Range: 1.5514. Min Range: -1.5514

Max Act: 1.2270. Min Act: -0.0001

Data Index: 741167 (C4 (Web Text))

Max Activating Token Index: 132

Text #10

Max Range: 1.5514. Min Range: -1.5514

Max Act: 1.3266. Min Act: -0.0001

Data Index: 566933 (C4 (Web Text))

Max Activating Token Index: 159

Text #11

Max Range: 1.5514. Min Range: -1.5514

Max Act: 1.1939. Min Act: -0.0000

Data Index: 387423 (C4 (Web Text))

Max Activating Token Index: 714

Text #12

Max Range: 1.5514. Min Range: -1.5514

Max Act: 1.1186. Min Act: -0.0001

Data Index: 1067063 (C4 (Web Text))

Max Activating Token Index: 437

Text #13

Max Range: 1.5514. Min Range: -1.5514

Max Act: 1.1164. Min Act: -0.0000

Data Index: 912740 (C4 (Web Text))

Max Activating Token Index: 390

Text #14

Max Range: 1.5514. Min Range: -1.5514

Max Act: 1.1122. Min Act: -0.0001

Data Index: 851524 (C4 (Web Text))

Max Activating Token Index: 688

Text #15

Max Range: 1.5514. Min Range: -1.5514

Max Act: 1.1666. Min Act: -0.0001

Data Index: 179163 (C4 (Web Text))

Max Activating Token Index: 53

Text #16

Max Range: 1.5514. Min Range: -1.5514

Max Act: 1.0994. Min Act: -0.0001

Data Index: 535733 (C4 (Web Text))

Max Activating Token Index: 440

Text #17

Max Range: 1.5514. Min Range: -1.5514

Max Act: 1.0910. Min Act: -0.0001

Data Index: 133376 (C4 (Web Text))

Max Activating Token Index: 657

Text #18

Max Range: 1.5514. Min Range: -1.5514

Max Act: 1.1634. Min Act: -0.0000

Data Index: 393882 (C4 (Web Text))

Max Activating Token Index: 454

Text #19

Max Range: 1.5514. Min Range: -1.5514

Max Act: 1.0732. Min Act: -0.0001

Data Index: 1117887 (C4 (Web Text))

Max Activating Token Index: 721