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

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

Neuron 445 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: 0.5639. Min Range: -0.5639

Max Act: 0.5639. Min Act: -0.0000

Data Index: 1051012 (C4 (Web Text))

Max Activating Token Index: 44

Text #1

Max Range: 0.5639. Min Range: -0.5639

Max Act: 0.4961. Min Act: -0.0000

Data Index: 393619 (C4 (Web Text))

Max Activating Token Index: 478

Text #2

Max Range: 0.5639. Min Range: -0.5639

Max Act: 0.5117. Min Act: -0.0000

Data Index: 1187918 (C4 (Web Text))

Max Activating Token Index: 284

Text #3

Max Range: 0.5639. Min Range: -0.5639

Max Act: 0.4444. Min Act: -0.0000

Data Index: 719912 (C4 (Web Text))

Max Activating Token Index: 507

Text #4

Max Range: 0.5639. Min Range: -0.5639

Max Act: 0.4797. Min Act: -0.0000

Data Index: 881287 (C4 (Web Text))

Max Activating Token Index: 949

Text #5

Max Range: 0.5639. Min Range: -0.5639

Max Act: 0.4442. Min Act: -0.0000

Data Index: 899541 (C4 (Web Text))

Max Activating Token Index: 654

Text #6

Max Range: 0.5639. Min Range: -0.5639

Max Act: 0.4106. Min Act: -0.0000

Data Index: 1266900 (C4 (Web Text))

Max Activating Token Index: 1005

Text #7

Max Range: 0.5639. Min Range: -0.5639

Max Act: 0.4107. Min Act: -0.0000

Data Index: 216070 (C4 (Web Text))

Max Activating Token Index: 760

Text #8

Max Range: 0.5639. Min Range: -0.5639

Max Act: 0.4293. Min Act: -0.0000

Data Index: 127766 (C4 (Web Text))

Max Activating Token Index: 222

Text #9

Max Range: 0.5639. Min Range: -0.5639

Max Act: 0.3783. Min Act: -0.0000

Data Index: 1289446 (C4 (Web Text))

Max Activating Token Index: 374

Text #10

Max Range: 0.5639. Min Range: -0.5639

Max Act: 0.4007. Min Act: -0.0000

Data Index: 944460 (C4 (Web Text))

Max Activating Token Index: 92

Text #11

Max Range: 0.5639. Min Range: -0.5639

Max Act: 0.4137. Min Act: -0.0001

Data Index: 390818 (C4 (Web Text))

Max Activating Token Index: 705

Text #12

Max Range: 0.5639. Min Range: -0.5639

Max Act: 0.3947. Min Act: -0.0000

Data Index: 81423 (C4 (Web Text))

Max Activating Token Index: 170

Text #13

Max Range: 0.5639. Min Range: -0.5639

Max Act: 0.3974. Min Act: 0.0001

Data Index: 487949 (C4 (Web Text))

Max Activating Token Index: 570

Text #14

Max Range: 0.5639. Min Range: -0.5639

Max Act: 0.4030. Min Act: -0.0000

Data Index: 257414 (C4 (Web Text))

Max Activating Token Index: 854

Text #15

Max Range: 0.5639. Min Range: -0.5639

Max Act: 0.4488. Min Act: -0.0000

Data Index: 969194 (C4 (Web Text))

Max Activating Token Index: 810

Text #16

Max Range: 0.5639. Min Range: -0.5639

Max Act: 0.4011. Min Act: -0.0000

Data Index: 342229 (C4 (Web Text))

Max Activating Token Index: 112

Text #17

Max Range: 0.5639. Min Range: -0.5639

Max Act: 0.3986. Min Act: -0.0000

Data Index: 1262878 (C4 (Web Text))

Max Activating Token Index: 853

Text #18

Max Range: 0.5639. Min Range: -0.5639

Max Act: 0.3833. Min Act: -0.0001

Data Index: 446696 (C4 (Web Text))

Max Activating Token Index: 275

Text #19

Max Range: 0.5639. Min Range: -0.5639

Max Act: 0.4060. Min Act: 0.0001

Data Index: 1026232 (C4 (Web Text))

Max Activating Token Index: 991