Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3701 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.7905. Min Range: -0.7905

Max Act: 0.7905. Min Act: -0.0000

Data Index: 401211 (C4 (Web Text))

Max Activating Token Index: 839

Text #1

Max Range: 0.7905. Min Range: -0.7905

Max Act: 0.7171. Min Act: -0.0000

Data Index: 213233 (C4 (Web Text))

Max Activating Token Index: 950

Text #2

Max Range: 0.7905. Min Range: -0.7905

Max Act: 0.7450. Min Act: -0.0000

Data Index: 369765 (C4 (Web Text))

Max Activating Token Index: 569

Text #3

Max Range: 0.7905. Min Range: -0.7905

Max Act: 0.6532. Min Act: -0.0000

Data Index: 795405 (C4 (Web Text))

Max Activating Token Index: 869

Text #4

Max Range: 0.7905. Min Range: -0.7905

Max Act: 0.6327. Min Act: -0.0000

Data Index: 562741 (C4 (Web Text))

Max Activating Token Index: 560

Text #5

Max Range: 0.7905. Min Range: -0.7905

Max Act: 0.6400. Min Act: -0.0000

Data Index: 45005 (C4 (Web Text))

Max Activating Token Index: 953

Text #6

Max Range: 0.7905. Min Range: -0.7905

Max Act: 0.5964. Min Act: -0.0000

Data Index: 1223965 (C4 (Web Text))

Max Activating Token Index: 929

Text #7

Max Range: 0.7905. Min Range: -0.7905

Max Act: 0.5842. Min Act: -0.0000

Data Index: 1342857 (C4 (Web Text))

Max Activating Token Index: 690

Text #8

Max Range: 0.7905. Min Range: -0.7905

Max Act: 0.5768. Min Act: -0.0000

Data Index: 792890 (C4 (Web Text))

Max Activating Token Index: 148

Text #9

Max Range: 0.7905. Min Range: -0.7905

Max Act: 0.5802. Min Act: -0.0000

Data Index: 195997 (C4 (Web Text))

Max Activating Token Index: 749

Text #10

Max Range: 0.7905. Min Range: -0.7905

Max Act: 0.5713. Min Act: -0.0000

Data Index: 665632 (C4 (Web Text))

Max Activating Token Index: 110

Text #11

Max Range: 0.7905. Min Range: -0.7905

Max Act: 0.5558. Min Act: -0.0000

Data Index: 1204296 (C4 (Web Text))

Max Activating Token Index: 496

Text #12

Max Range: 0.7905. Min Range: -0.7905

Max Act: 0.5032. Min Act: -0.0000

Data Index: 1234526 (C4 (Web Text))

Max Activating Token Index: 791

Text #13

Max Range: 0.7905. Min Range: -0.7905

Max Act: 0.5420. Min Act: -0.0000

Data Index: 343096 (C4 (Web Text))

Max Activating Token Index: 389

Text #14

Max Range: 0.7905. Min Range: -0.7905

Max Act: 0.5413. Min Act: -0.0000

Data Index: 1332600 (C4 (Web Text))

Max Activating Token Index: 676

Text #15

Max Range: 0.7905. Min Range: -0.7905

Max Act: 0.5557. Min Act: -0.0000

Data Index: 787101 (C4 (Web Text))

Max Activating Token Index: 438

Text #16

Max Range: 0.7905. Min Range: -0.7905

Max Act: 0.5091. Min Act: -0.0000

Data Index: 68832 (C4 (Web Text))

Max Activating Token Index: 265

Text #17

Max Range: 0.7905. Min Range: -0.7905

Max Act: 0.5295. Min Act: -0.0000

Data Index: 35714 (C4 (Web Text))

Max Activating Token Index: 510

Text #18

Max Range: 0.7905. Min Range: -0.7905

Max Act: 0.5270. Min Act: -0.0000

Data Index: 552269 (C4 (Web Text))

Max Activating Token Index: 511

Text #19

Max Range: 0.7905. Min Range: -0.7905

Max Act: 0.5039. Min Act: -0.0000

Data Index: 701101 (C4 (Web Text))

Max Activating Token Index: 623