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

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

Neuron 4003 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: 1.5037. Min Range: -1.5037

Max Act: 1.5037. Min Act: -0.0002

Data Index: 1084031 (C4 (Web Text))

Max Activating Token Index: 13

Text #1

Max Range: 1.5037. Min Range: -1.5037

Max Act: 1.4473. Min Act: -0.0002

Data Index: 88591 (C4 (Web Text))

Max Activating Token Index: 264

Text #2

Max Range: 1.5037. Min Range: -1.5037

Max Act: 1.4645. Min Act: -0.0002

Data Index: 938233 (C4 (Web Text))

Max Activating Token Index: 336

Text #3

Max Range: 1.5037. Min Range: -1.5037

Max Act: 1.2557. Min Act: -0.0002

Data Index: 173642 (C4 (Web Text))

Max Activating Token Index: 602

Text #4

Max Range: 1.5037. Min Range: -1.5037

Max Act: 1.3382. Min Act: -0.0001

Data Index: 384457 (C4 (Web Text))

Max Activating Token Index: 947

Text #5

Max Range: 1.5037. Min Range: -1.5037

Max Act: 1.2846. Min Act: -0.0001

Data Index: 686089 (C4 (Web Text))

Max Activating Token Index: 23

Text #6

Max Range: 1.5037. Min Range: -1.5037

Max Act: 1.2054. Min Act: -0.0002

Data Index: 512339 (C4 (Web Text))

Max Activating Token Index: 449

Text #7

Max Range: 1.5037. Min Range: -1.5037

Max Act: 1.3468. Min Act: -0.0002

Data Index: 1280693 (C4 (Web Text))

Max Activating Token Index: 292

Text #8

Max Range: 1.5037. Min Range: -1.5037

Max Act: 1.2566. Min Act: -0.0002

Data Index: 265572 (C4 (Web Text))

Max Activating Token Index: 597

Text #9

Max Range: 1.5037. Min Range: -1.5037

Max Act: 1.2214. Min Act: -0.0002

Data Index: 1254135 (C4 (Web Text))

Max Activating Token Index: 525

Text #10

Max Range: 1.5037. Min Range: -1.5037

Max Act: 1.2277. Min Act: -0.0001

Data Index: 456659 (C4 (Web Text))

Max Activating Token Index: 873

Text #11

Max Range: 1.5037. Min Range: -1.5037

Max Act: 1.1289. Min Act: -0.0002

Data Index: 1054178 (C4 (Web Text))

Max Activating Token Index: 708

Text #12

Max Range: 1.5037. Min Range: -1.5037

Max Act: 1.1908. Min Act: -0.0001

Data Index: 842661 (C4 (Web Text))

Max Activating Token Index: 850

Text #13

Max Range: 1.5037. Min Range: -1.5037

Max Act: 1.1557. Min Act: -0.0002

Data Index: 572193 (C4 (Web Text))

Max Activating Token Index: 437

Text #14

Max Range: 1.5037. Min Range: -1.5037

Max Act: 1.1080. Min Act: -0.0002

Data Index: 1005104 (C4 (Web Text))

Max Activating Token Index: 694

Text #15

Max Range: 1.5037. Min Range: -1.5037

Max Act: 1.1454. Min Act: -0.0001

Data Index: 328455 (C4 (Web Text))

Max Activating Token Index: 596

Text #16

Max Range: 1.5037. Min Range: -1.5037

Max Act: 1.2088. Min Act: -0.0002

Data Index: 1302800 (C4 (Web Text))

Max Activating Token Index: 408

Text #17

Max Range: 1.5037. Min Range: -1.5037

Max Act: 1.0782. Min Act: -0.0002

Data Index: 1196507 (C4 (Web Text))

Max Activating Token Index: 835

Text #18

Max Range: 1.5037. Min Range: -1.5037

Max Act: 1.1686. Min Act: -0.0002

Data Index: 1243656 (C4 (Web Text))

Max Activating Token Index: 220

Text #19

Max Range: 1.5037. Min Range: -1.5037

Max Act: 1.1529. Min Act: -0.0002

Data Index: 794619 (C4 (Web Text))

Max Activating Token Index: 620