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

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

Neuron 1709 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5937. Min Range: -1.5937

Max Act: 1.5297. Min Act: -0.0001

Data Index: 1197832 (C4 (Web Text))

Max Activating Token Index: 1002

Text #1

Max Range: 1.5937. Min Range: -1.5937

Max Act: 1.5937. Min Act: -0.0001

Data Index: 1142159 (C4 (Web Text))

Max Activating Token Index: 548

Text #2

Max Range: 1.5937. Min Range: -1.5937

Max Act: 1.4226. Min Act: -0.0001

Data Index: 802935 (C4 (Web Text))

Max Activating Token Index: 15

Text #3

Max Range: 1.5937. Min Range: -1.5937

Max Act: 1.4322. Min Act: -0.0001

Data Index: 917382 (C4 (Web Text))

Max Activating Token Index: 837

Text #4

Max Range: 1.5937. Min Range: -1.5937

Max Act: 1.1589. Min Act: -0.0001

Data Index: 941713 (C4 (Web Text))

Max Activating Token Index: 45

Text #5

Max Range: 1.5937. Min Range: -1.5937

Max Act: 1.1436. Min Act: -0.0001

Data Index: 306082 (C4 (Web Text))

Max Activating Token Index: 67

Text #6

Max Range: 1.5937. Min Range: -1.5937

Max Act: 1.1071. Min Act: -0.0001

Data Index: 295274 (C4 (Web Text))

Max Activating Token Index: 118

Text #7

Max Range: 1.5937. Min Range: -1.5937

Max Act: 1.1263. Min Act: -0.0001

Data Index: 787271 (C4 (Web Text))

Max Activating Token Index: 129

Text #8

Max Range: 1.5937. Min Range: -1.5937

Max Act: 1.0871. Min Act: -0.0001

Data Index: 152507 (C4 (Web Text))

Max Activating Token Index: 342

Text #9

Max Range: 1.5937. Min Range: -1.5937

Max Act: 1.0725. Min Act: -0.0001

Data Index: 1030369 (C4 (Web Text))

Max Activating Token Index: 109

Text #10

Max Range: 1.5937. Min Range: -1.5937

Max Act: 1.0592. Min Act: -0.0001

Data Index: 1047554 (C4 (Web Text))

Max Activating Token Index: 273

Text #11

Max Range: 1.5937. Min Range: -1.5937

Max Act: 0.9900. Min Act: -0.0001

Data Index: 950922 (C4 (Web Text))

Max Activating Token Index: 307

Text #12

Max Range: 1.5937. Min Range: -1.5937

Max Act: 1.1465. Min Act: -0.0001

Data Index: 500689 (C4 (Web Text))

Max Activating Token Index: 822

Text #13

Max Range: 1.5937. Min Range: -1.5937

Max Act: 0.9693. Min Act: -0.0001

Data Index: 930053 (C4 (Web Text))

Max Activating Token Index: 260

Text #14

Max Range: 1.5937. Min Range: -1.5937

Max Act: 1.0769. Min Act: -0.0001

Data Index: 434238 (C4 (Web Text))

Max Activating Token Index: 823

Text #15

Max Range: 1.5937. Min Range: -1.5937

Max Act: 1.0420. Min Act: -0.0001

Data Index: 513762 (C4 (Web Text))

Max Activating Token Index: 505

Text #16

Max Range: 1.5937. Min Range: -1.5937

Max Act: 0.9620. Min Act: -0.0001

Data Index: 1333588 (C4 (Web Text))

Max Activating Token Index: 941

Text #17

Max Range: 1.5937. Min Range: -1.5937

Max Act: 0.9546. Min Act: -0.0001

Data Index: 937056 (C4 (Web Text))

Max Activating Token Index: 21

Text #18

Max Range: 1.5937. Min Range: -1.5937

Max Act: 0.9622. Min Act: -0.0001

Data Index: 100407 (C4 (Web Text))

Max Activating Token Index: 593

Text #19

Max Range: 1.5937. Min Range: -1.5937

Max Act: 0.9145. Min Act: -0.0001

Data Index: 1060505 (C4 (Web Text))

Max Activating Token Index: 796