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

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

Neuron 2791 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6766. Min Range: -1.6766

Max Act: 1.6766. Min Act: -0.0001

Data Index: 155261 (C4 (Web Text))

Max Activating Token Index: 341

Text #1

Max Range: 1.6766. Min Range: -1.6766

Max Act: 1.2803. Min Act: -0.0001

Data Index: 720457 (C4 (Web Text))

Max Activating Token Index: 757

Text #2

Max Range: 1.6766. Min Range: -1.6766

Max Act: 1.3235. Min Act: -0.0001

Data Index: 671435 (C4 (Web Text))

Max Activating Token Index: 231

Text #3

Max Range: 1.6766. Min Range: -1.6766

Max Act: 1.3223. Min Act: -0.0002

Data Index: 777896 (C4 (Web Text))

Max Activating Token Index: 334

Text #4

Max Range: 1.6766. Min Range: -1.6766

Max Act: 1.3468. Min Act: -0.0002

Data Index: 1252585 (C4 (Web Text))

Max Activating Token Index: 391

Text #5

Max Range: 1.6766. Min Range: -1.6766

Max Act: 1.1359. Min Act: -0.0001

Data Index: 720025 (C4 (Web Text))

Max Activating Token Index: 649

Text #6

Max Range: 1.6766. Min Range: -1.6766

Max Act: 1.1655. Min Act: -0.0001

Data Index: 804133 (C4 (Web Text))

Max Activating Token Index: 885

Text #7

Max Range: 1.6766. Min Range: -1.6766

Max Act: 1.1418. Min Act: -0.0001

Data Index: 1342481 (C4 (Web Text))

Max Activating Token Index: 938

Text #8

Max Range: 1.6766. Min Range: -1.6766

Max Act: 1.1271. Min Act: -0.0001

Data Index: 1119972 (C4 (Web Text))

Max Activating Token Index: 943

Text #9

Max Range: 1.6766. Min Range: -1.6766

Max Act: 1.1594. Min Act: -0.0001

Data Index: 1339953 (C4 (Web Text))

Max Activating Token Index: 486

Text #10

Max Range: 1.6766. Min Range: -1.6766

Max Act: 1.0635. Min Act: -0.0002

Data Index: 812108 (C4 (Web Text))

Max Activating Token Index: 384

Text #11

Max Range: 1.6766. Min Range: -1.6766

Max Act: 1.1556. Min Act: -0.0002

Data Index: 723416 (C4 (Web Text))

Max Activating Token Index: 969

Text #12

Max Range: 1.6766. Min Range: -1.6766

Max Act: 1.1919. Min Act: -0.0002

Data Index: 1323332 (C4 (Web Text))

Max Activating Token Index: 221

Text #13

Max Range: 1.6766. Min Range: -1.6766

Max Act: 1.0698. Min Act: -0.0001

Data Index: 993259 (C4 (Web Text))

Max Activating Token Index: 910

Text #14

Max Range: 1.6766. Min Range: -1.6766

Max Act: 1.1033. Min Act: -0.0001

Data Index: 1035138 (C4 (Web Text))

Max Activating Token Index: 420

Text #15

Max Range: 1.6766. Min Range: -1.6766

Max Act: 1.0677. Min Act: -0.0002

Data Index: 959101 (C4 (Web Text))

Max Activating Token Index: 833

Text #16

Max Range: 1.6766. Min Range: -1.6766

Max Act: 1.1201. Min Act: -0.0001

Data Index: 1149641 (C4 (Web Text))

Max Activating Token Index: 949

Text #17

Max Range: 1.6766. Min Range: -1.6766

Max Act: 1.0454. Min Act: -0.0002

Data Index: 310169 (C4 (Web Text))

Max Activating Token Index: 925

Text #18

Max Range: 1.6766. Min Range: -1.6766

Max Act: 1.1531. Min Act: -0.0002

Data Index: 1084972 (C4 (Web Text))

Max Activating Token Index: 290

Text #19

Max Range: 1.6766. Min Range: -1.6766

Max Act: 1.0175. Min Act: -0.0002

Data Index: 537870 (C4 (Web Text))

Max Activating Token Index: 957