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

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

Neuron 640 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3574. Min Range: -0.3574

Max Act: 0.3574. Min Act: -0.0001

Data Index: 392468 (C4 (Web Text))

Max Activating Token Index: 965

Text #1

Max Range: 0.3574. Min Range: -0.3574

Max Act: 0.3362. Min Act: -0.0001

Data Index: 183887 (C4 (Web Text))

Max Activating Token Index: 396

Text #2

Max Range: 0.3574. Min Range: -0.3574

Max Act: 0.3134. Min Act: -0.0001

Data Index: 930962 (C4 (Web Text))

Max Activating Token Index: 608

Text #3

Max Range: 0.3574. Min Range: -0.3574

Max Act: 0.3173. Min Act: -0.0001

Data Index: 879137 (C4 (Web Text))

Max Activating Token Index: 23

Text #4

Max Range: 0.3574. Min Range: -0.3574

Max Act: 0.2769. Min Act: -0.0001

Data Index: 1158253 (C4 (Web Text))

Max Activating Token Index: 306

Text #5

Max Range: 0.3574. Min Range: -0.3574

Max Act: 0.2935. Min Act: -0.0001

Data Index: 1053427 (C4 (Web Text))

Max Activating Token Index: 682

Text #6

Max Range: 0.3574. Min Range: -0.3574

Max Act: 0.2877. Min Act: -0.0001

Data Index: 1259958 (C4 (Web Text))

Max Activating Token Index: 384

Text #7

Max Range: 0.3574. Min Range: -0.3574

Max Act: 0.2857. Min Act: -0.0001

Data Index: 564951 (C4 (Web Text))

Max Activating Token Index: 237

Text #8

Max Range: 0.3574. Min Range: -0.3574

Max Act: 0.2708. Min Act: -0.0001

Data Index: 510256 (C4 (Web Text))

Max Activating Token Index: 308

Text #9

Max Range: 0.3574. Min Range: -0.3574

Max Act: 0.2790. Min Act: -0.0001

Data Index: 973019 (C4 (Web Text))

Max Activating Token Index: 570

Text #10

Max Range: 0.3574. Min Range: -0.3574

Max Act: 0.2600. Min Act: -0.0001

Data Index: 138636 (C4 (Web Text))

Max Activating Token Index: 747

Text #11

Max Range: 0.3574. Min Range: -0.3574

Max Act: 0.2848. Min Act: -0.0001

Data Index: 43666 (C4 (Web Text))

Max Activating Token Index: 834

Text #12

Max Range: 0.3574. Min Range: -0.3574

Max Act: 0.2723. Min Act: -0.0001

Data Index: 1356626 (C4 (Web Text))

Max Activating Token Index: 252

Text #13

Max Range: 0.3574. Min Range: -0.3574

Max Act: 0.2805. Min Act: -0.0001

Data Index: 857541 (C4 (Web Text))

Max Activating Token Index: 879

Text #14

Max Range: 0.3574. Min Range: -0.3574

Max Act: 0.2811. Min Act: -0.0001

Data Index: 363037 (C4 (Web Text))

Max Activating Token Index: 863

Text #15

Max Range: 0.3574. Min Range: -0.3574

Max Act: 0.2801. Min Act: -0.0001

Data Index: 276968 (C4 (Web Text))

Max Activating Token Index: 600

Text #16

Max Range: 0.3574. Min Range: -0.3574

Max Act: 0.2687. Min Act: -0.0001

Data Index: 998110 (C4 (Web Text))

Max Activating Token Index: 275

Text #17

Max Range: 0.3574. Min Range: -0.3574

Max Act: 0.2431. Min Act: -0.0001

Data Index: 550293 (C4 (Web Text))

Max Activating Token Index: 168

Text #18

Max Range: 0.3574. Min Range: -0.3574

Max Act: 0.2655. Min Act: -0.0001

Data Index: 1298206 (C4 (Web Text))

Max Activating Token Index: 17

Text #19

Max Range: 0.3574. Min Range: -0.3574

Max Act: 0.2475. Min Act: -0.0001

Data Index: 347330 (C4 (Web Text))

Max Activating Token Index: 729