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

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

Neuron 993 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1246. Min Range: -2.1246

Max Act: 2.1246. Min Act: -0.0000

Data Index: 908090 (C4 (Web Text))

Max Activating Token Index: 700

Text #1

Max Range: 2.1246. Min Range: -2.1246

Max Act: 1.7225. Min Act: -0.0000

Data Index: 916684 (C4 (Web Text))

Max Activating Token Index: 53

Text #2

Max Range: 2.1246. Min Range: -2.1246

Max Act: 1.4562. Min Act: -0.0000

Data Index: 130545 (C4 (Web Text))

Max Activating Token Index: 863

Text #3

Max Range: 2.1246. Min Range: -2.1246

Max Act: 1.5985. Min Act: -0.0001

Data Index: 78507 (C4 (Web Text))

Max Activating Token Index: 555

Text #4

Max Range: 2.1246. Min Range: -2.1246

Max Act: 1.5864. Min Act: -0.0000

Data Index: 1146103 (C4 (Web Text))

Max Activating Token Index: 949

Text #5

Max Range: 2.1246. Min Range: -2.1246

Max Act: 1.3434. Min Act: -0.0000

Data Index: 1195082 (C4 (Web Text))

Max Activating Token Index: 237

Text #6

Max Range: 2.1246. Min Range: -2.1246

Max Act: 1.4176. Min Act: -0.0000

Data Index: 1544 (C4 (Web Text))

Max Activating Token Index: 959

Text #7

Max Range: 2.1246. Min Range: -2.1246

Max Act: 1.5776. Min Act: -0.0000

Data Index: 411290 (C4 (Web Text))

Max Activating Token Index: 786

Text #8

Max Range: 2.1246. Min Range: -2.1246

Max Act: 1.5113. Min Act: -0.0000

Data Index: 724469 (C4 (Web Text))

Max Activating Token Index: 800

Text #9

Max Range: 2.1246. Min Range: -2.1246

Max Act: 1.0970. Min Act: -0.0000

Data Index: 1225718 (C4 (Web Text))

Max Activating Token Index: 753

Text #10

Max Range: 2.1246. Min Range: -2.1246

Max Act: 1.4896. Min Act: -0.0000

Data Index: 217405 (C4 (Web Text))

Max Activating Token Index: 135

Text #11

Max Range: 2.1246. Min Range: -2.1246

Max Act: 1.3468. Min Act: -0.0000

Data Index: 467490 (C4 (Web Text))

Max Activating Token Index: 154

Text #12

Max Range: 2.1246. Min Range: -2.1246

Max Act: 1.3233. Min Act: -0.0000

Data Index: 607969 (C4 (Web Text))

Max Activating Token Index: 188

Text #13

Max Range: 2.1246. Min Range: -2.1246

Max Act: 1.1899. Min Act: -0.0000

Data Index: 517976 (C4 (Web Text))

Max Activating Token Index: 161

Text #14

Max Range: 2.1246. Min Range: -2.1246

Max Act: 1.5490. Min Act: -0.0000

Data Index: 248303 (C4 (Web Text))

Max Activating Token Index: 126

Text #15

Max Range: 2.1246. Min Range: -2.1246

Max Act: 1.3481. Min Act: -0.0000

Data Index: 8627 (C4 (Web Text))

Max Activating Token Index: 967

Text #16

Max Range: 2.1246. Min Range: -2.1246

Max Act: 1.4041. Min Act: -0.0000

Data Index: 1089030 (C4 (Web Text))

Max Activating Token Index: 934

Text #17

Max Range: 2.1246. Min Range: -2.1246

Max Act: 1.2872. Min Act: -0.0000

Data Index: 1296778 (C4 (Web Text))

Max Activating Token Index: 595

Text #18

Max Range: 2.1246. Min Range: -2.1246

Max Act: 1.3771. Min Act: -0.0000

Data Index: 273694 (C4 (Web Text))

Max Activating Token Index: 446

Text #19

Max Range: 2.1246. Min Range: -2.1246

Max Act: 1.3372. Min Act: -0.0000

Data Index: 610760 (C4 (Web Text))

Max Activating Token Index: 671