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

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

Neuron 3146 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7747. Min Range: -0.7747

Max Act: 0.7577. Min Act: -0.0001

Data Index: 1318484 (C4 (Web Text))

Max Activating Token Index: 156

Text #1

Max Range: 0.7747. Min Range: -0.7747

Max Act: 0.7577. Min Act: -0.0001

Data Index: 106158 (C4 (Web Text))

Max Activating Token Index: 542

Text #2

Max Range: 0.7747. Min Range: -0.7747

Max Act: 0.7441. Min Act: -0.0001

Data Index: 13923 (C4 (Web Text))

Max Activating Token Index: 782

Text #3

Max Range: 0.7747. Min Range: -0.7747

Max Act: 0.7387. Min Act: -0.0001

Data Index: 157798 (C4 (Web Text))

Max Activating Token Index: 362

Text #4

Max Range: 0.7747. Min Range: -0.7747

Max Act: 0.7380. Min Act: -0.0001

Data Index: 10710 (C4 (Web Text))

Max Activating Token Index: 300

Text #5

Max Range: 0.7747. Min Range: -0.7747

Max Act: 0.7148. Min Act: -0.0001

Data Index: 248116 (C4 (Web Text))

Max Activating Token Index: 246

Text #6

Max Range: 0.7747. Min Range: -0.7747

Max Act: 0.7578. Min Act: -0.0001

Data Index: 1125355 (C4 (Web Text))

Max Activating Token Index: 117

Text #7

Max Range: 0.7747. Min Range: -0.7747

Max Act: 0.7747. Min Act: -0.0001

Data Index: 10096 (C4 (Web Text))

Max Activating Token Index: 257

Text #8

Max Range: 0.7747. Min Range: -0.7747

Max Act: 0.7046. Min Act: -0.0001

Data Index: 132156 (C4 (Web Text))

Max Activating Token Index: 612

Text #9

Max Range: 0.7747. Min Range: -0.7747

Max Act: 0.7117. Min Act: -0.0001

Data Index: 383045 (C4 (Web Text))

Max Activating Token Index: 903

Text #10

Max Range: 0.7747. Min Range: -0.7747

Max Act: 0.7433. Min Act: -0.0000

Data Index: 531121 (C4 (Web Text))

Max Activating Token Index: 648

Text #11

Max Range: 0.7747. Min Range: -0.7747

Max Act: 0.7327. Min Act: -0.0001

Data Index: 246455 (C4 (Web Text))

Max Activating Token Index: 816

Text #12

Max Range: 0.7747. Min Range: -0.7747

Max Act: 0.7224. Min Act: -0.0001

Data Index: 862155 (C4 (Web Text))

Max Activating Token Index: 261

Text #13

Max Range: 0.7747. Min Range: -0.7747

Max Act: 0.7465. Min Act: -0.0001

Data Index: 492628 (C4 (Web Text))

Max Activating Token Index: 996

Text #14

Max Range: 0.7747. Min Range: -0.7747

Max Act: 0.6810. Min Act: -0.0001

Data Index: 175627 (C4 (Web Text))

Max Activating Token Index: 779

Text #15

Max Range: 0.7747. Min Range: -0.7747

Max Act: 0.7139. Min Act: -0.0001

Data Index: 680490 (C4 (Web Text))

Max Activating Token Index: 527

Text #16

Max Range: 0.7747. Min Range: -0.7747

Max Act: 0.6906. Min Act: -0.0001

Data Index: 56387 (C4 (Web Text))

Max Activating Token Index: 777

Text #17

Max Range: 0.7747. Min Range: -0.7747

Max Act: 0.7402. Min Act: -0.0001

Data Index: 387091 (C4 (Web Text))

Max Activating Token Index: 732

Text #18

Max Range: 0.7747. Min Range: -0.7747

Max Act: 0.6504. Min Act: -0.0001

Data Index: 1010017 (C4 (Web Text))

Max Activating Token Index: 675

Text #19

Max Range: 0.7747. Min Range: -0.7747

Max Act: 0.6932. Min Act: -0.0001

Data Index: 777917 (C4 (Web Text))

Max Activating Token Index: 450