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

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

Neuron 2664 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: 1.3324. Min Range: -1.3324

Max Act: 1.3324. Min Act: -0.0001

Data Index: 706146 (C4 (Web Text))

Max Activating Token Index: 495

Text #1

Max Range: 1.3324. Min Range: -1.3324

Max Act: 1.1277. Min Act: -0.0001

Data Index: 900816 (C4 (Web Text))

Max Activating Token Index: 956

Text #2

Max Range: 1.3324. Min Range: -1.3324

Max Act: 1.1157. Min Act: -0.0001

Data Index: 52474 (C4 (Web Text))

Max Activating Token Index: 584

Text #3

Max Range: 1.3324. Min Range: -1.3324

Max Act: 1.0885. Min Act: -0.0001

Data Index: 983083 (C4 (Web Text))

Max Activating Token Index: 36

Text #4

Max Range: 1.3324. Min Range: -1.3324

Max Act: 1.0805. Min Act: -0.0001

Data Index: 988441 (C4 (Web Text))

Max Activating Token Index: 249

Text #5

Max Range: 1.3324. Min Range: -1.3324

Max Act: 1.0347. Min Act: -0.0001

Data Index: 486035 (C4 (Web Text))

Max Activating Token Index: 386

Text #6

Max Range: 1.3324. Min Range: -1.3324

Max Act: 1.0330. Min Act: -0.0001

Data Index: 761338 (C4 (Web Text))

Max Activating Token Index: 711

Text #7

Max Range: 1.3324. Min Range: -1.3324

Max Act: 1.0225. Min Act: -0.0001

Data Index: 1337590 (C4 (Web Text))

Max Activating Token Index: 8

Text #8

Max Range: 1.3324. Min Range: -1.3324

Max Act: 1.0419. Min Act: -0.0001

Data Index: 518171 (C4 (Web Text))

Max Activating Token Index: 961

Text #9

Max Range: 1.3324. Min Range: -1.3324

Max Act: 1.0040. Min Act: -0.0001

Data Index: 894378 (C4 (Web Text))

Max Activating Token Index: 905

Text #10

Max Range: 1.3324. Min Range: -1.3324

Max Act: 1.0680. Min Act: -0.0001

Data Index: 135418 (C4 (Web Text))

Max Activating Token Index: 468

Text #11

Max Range: 1.3324. Min Range: -1.3324

Max Act: 0.9954. Min Act: -0.0001

Data Index: 851402 (C4 (Web Text))

Max Activating Token Index: 444

Text #12

Max Range: 1.3324. Min Range: -1.3324

Max Act: 0.9649. Min Act: -0.0001

Data Index: 756496 (C4 (Web Text))

Max Activating Token Index: 501

Text #13

Max Range: 1.3324. Min Range: -1.3324

Max Act: 0.9914. Min Act: -0.0001

Data Index: 1034583 (C4 (Web Text))

Max Activating Token Index: 524

Text #14

Max Range: 1.3324. Min Range: -1.3324

Max Act: 0.9862. Min Act: -0.0001

Data Index: 478496 (C4 (Web Text))

Max Activating Token Index: 168

Text #15

Max Range: 1.3324. Min Range: -1.3324

Max Act: 0.9857. Min Act: -0.0001

Data Index: 162298 (C4 (Web Text))

Max Activating Token Index: 496

Text #16

Max Range: 1.3324. Min Range: -1.3324

Max Act: 1.0143. Min Act: -0.0001

Data Index: 1269529 (C4 (Web Text))

Max Activating Token Index: 830

Text #17

Max Range: 1.3324. Min Range: -1.3324

Max Act: 0.8990. Min Act: -0.0001

Data Index: 47681 (C4 (Web Text))

Max Activating Token Index: 639

Text #18

Max Range: 1.3324. Min Range: -1.3324

Max Act: 0.9869. Min Act: -0.0001

Data Index: 448333 (C4 (Web Text))

Max Activating Token Index: 405

Text #19

Max Range: 1.3324. Min Range: -1.3324

Max Act: 0.9267. Min Act: -0.0001

Data Index: 12310 (C4 (Web Text))

Max Activating Token Index: 561