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

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

Neuron 3220 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: 1.9355. Min Range: -1.9355

Max Act: 1.9355. Min Act: -0.0001

Data Index: 1071031 (C4 (Web Text))

Max Activating Token Index: 962

Text #1

Max Range: 1.9355. Min Range: -1.9355

Max Act: 1.8766. Min Act: -0.0001

Data Index: 708949 (C4 (Web Text))

Max Activating Token Index: 239

Text #2

Max Range: 1.9355. Min Range: -1.9355

Max Act: 1.7132. Min Act: -0.0001

Data Index: 326454 (C4 (Web Text))

Max Activating Token Index: 727

Text #3

Max Range: 1.9355. Min Range: -1.9355

Max Act: 1.6768. Min Act: -0.0001

Data Index: 452371 (C4 (Web Text))

Max Activating Token Index: 681

Text #4

Max Range: 1.9355. Min Range: -1.9355

Max Act: 1.6930. Min Act: -0.0001

Data Index: 67668 (C4 (Web Text))

Max Activating Token Index: 637

Text #5

Max Range: 1.9355. Min Range: -1.9355

Max Act: 1.7951. Min Act: -0.0001

Data Index: 510536 (C4 (Web Text))

Max Activating Token Index: 956

Text #6

Max Range: 1.9355. Min Range: -1.9355

Max Act: 1.7080. Min Act: -0.0001

Data Index: 1330840 (C4 (Web Text))

Max Activating Token Index: 354

Text #7

Max Range: 1.9355. Min Range: -1.9355

Max Act: 1.6821. Min Act: -0.0001

Data Index: 186415 (C4 (Web Text))

Max Activating Token Index: 857

Text #8

Max Range: 1.9355. Min Range: -1.9355

Max Act: 1.6153. Min Act: -0.0001

Data Index: 452695 (C4 (Web Text))

Max Activating Token Index: 37

Text #9

Max Range: 1.9355. Min Range: -1.9355

Max Act: 1.5700. Min Act: -0.0001

Data Index: 709110 (C4 (Web Text))

Max Activating Token Index: 1010

Text #10

Max Range: 1.9355. Min Range: -1.9355

Max Act: 1.5352. Min Act: -0.0001

Data Index: 1326641 (C4 (Web Text))

Max Activating Token Index: 978

Text #11

Max Range: 1.9355. Min Range: -1.9355

Max Act: 1.5377. Min Act: -0.0001

Data Index: 359595 (C4 (Web Text))

Max Activating Token Index: 443

Text #12

Max Range: 1.9355. Min Range: -1.9355

Max Act: 1.5785. Min Act: -0.0001

Data Index: 777325 (C4 (Web Text))

Max Activating Token Index: 732

Text #13

Max Range: 1.9355. Min Range: -1.9355

Max Act: 1.4921. Min Act: -0.0001

Data Index: 549138 (C4 (Web Text))

Max Activating Token Index: 934

Text #14

Max Range: 1.9355. Min Range: -1.9355

Max Act: 1.3892. Min Act: -0.0001

Data Index: 606430 (C4 (Web Text))

Max Activating Token Index: 318

Text #15

Max Range: 1.9355. Min Range: -1.9355

Max Act: 1.4143. Min Act: -0.0001

Data Index: 637392 (C4 (Web Text))

Max Activating Token Index: 494

Text #16

Max Range: 1.9355. Min Range: -1.9355

Max Act: 1.4639. Min Act: -0.0001

Data Index: 525030 (C4 (Web Text))

Max Activating Token Index: 661

Text #17

Max Range: 1.9355. Min Range: -1.9355

Max Act: 1.4031. Min Act: -0.0001

Data Index: 679333 (C4 (Web Text))

Max Activating Token Index: 997

Text #18

Max Range: 1.9355. Min Range: -1.9355

Max Act: 1.4754. Min Act: -0.0001

Data Index: 1150909 (C4 (Web Text))

Max Activating Token Index: 288

Text #19

Max Range: 1.9355. Min Range: -1.9355

Max Act: 1.4429. Min Act: -0.0001

Data Index: 1331933 (C4 (Web Text))

Max Activating Token Index: 817