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

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

Neuron 275 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4809. Min Range: -0.4809

Max Act: 0.4809. Min Act: -0.0000

Data Index: 1338675 (C4 (Web Text))

Max Activating Token Index: 284

Text #1

Max Range: 0.4809. Min Range: -0.4809

Max Act: 0.4337. Min Act: -0.0001

Data Index: 1337865 (C4 (Web Text))

Max Activating Token Index: 482

Text #2

Max Range: 0.4809. Min Range: -0.4809

Max Act: 0.4438. Min Act: -0.0000

Data Index: 1182623 (C4 (Web Text))

Max Activating Token Index: 758

Text #3

Max Range: 0.4809. Min Range: -0.4809

Max Act: 0.4114. Min Act: -0.0000

Data Index: 73834 (C4 (Web Text))

Max Activating Token Index: 915

Text #4

Max Range: 0.4809. Min Range: -0.4809

Max Act: 0.4461. Min Act: -0.0000

Data Index: 743252 (C4 (Web Text))

Max Activating Token Index: 166

Text #5

Max Range: 0.4809. Min Range: -0.4809

Max Act: 0.3568. Min Act: -0.0000

Data Index: 1299525 (C4 (Web Text))

Max Activating Token Index: 216

Text #6

Max Range: 0.4809. Min Range: -0.4809

Max Act: 0.3963. Min Act: -0.0000

Data Index: 1203283 (C4 (Web Text))

Max Activating Token Index: 610

Text #7

Max Range: 0.4809. Min Range: -0.4809

Max Act: 0.4003. Min Act: -0.0001

Data Index: 208349 (C4 (Web Text))

Max Activating Token Index: 347

Text #8

Max Range: 0.4809. Min Range: -0.4809

Max Act: 0.4035. Min Act: -0.0001

Data Index: 1345867 (C4 (Web Text))

Max Activating Token Index: 211

Text #9

Max Range: 0.4809. Min Range: -0.4809

Max Act: 0.4000. Min Act: -0.0001

Data Index: 1099650 (C4 (Web Text))

Max Activating Token Index: 886

Text #10

Max Range: 0.4809. Min Range: -0.4809

Max Act: 0.3716. Min Act: -0.0000

Data Index: 1228151 (C4 (Web Text))

Max Activating Token Index: 667

Text #11

Max Range: 0.4809. Min Range: -0.4809

Max Act: 0.3859. Min Act: -0.0000

Data Index: 35749 (C4 (Web Text))

Max Activating Token Index: 788

Text #12

Max Range: 0.4809. Min Range: -0.4809

Max Act: 0.3781. Min Act: -0.0000

Data Index: 1035821 (C4 (Web Text))

Max Activating Token Index: 560

Text #13

Max Range: 0.4809. Min Range: -0.4809

Max Act: 0.3733. Min Act: -0.0001

Data Index: 345260 (C4 (Web Text))

Max Activating Token Index: 668

Text #14

Max Range: 0.4809. Min Range: -0.4809

Max Act: 0.3608. Min Act: -0.0000

Data Index: 1093054 (C4 (Web Text))

Max Activating Token Index: 869

Text #15

Max Range: 0.4809. Min Range: -0.4809

Max Act: 0.3579. Min Act: -0.0001

Data Index: 1081545 (C4 (Web Text))

Max Activating Token Index: 949

Text #16

Max Range: 0.4809. Min Range: -0.4809

Max Act: 0.3991. Min Act: -0.0001

Data Index: 50032 (C4 (Web Text))

Max Activating Token Index: 1014

Text #17

Max Range: 0.4809. Min Range: -0.4809

Max Act: 0.4185. Min Act: -0.0000

Data Index: 102241 (C4 (Web Text))

Max Activating Token Index: 959

Text #18

Max Range: 0.4809. Min Range: -0.4809

Max Act: 0.3744. Min Act: -0.0000

Data Index: 832433 (C4 (Web Text))

Max Activating Token Index: 826

Text #19

Max Range: 0.4809. Min Range: -0.4809

Max Act: 0.3725. Min Act: -0.0000

Data Index: 1478976 (Python Code)

Max Activating Token Index: 11