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

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

Neuron 4742 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6245. Min Range: -0.6245

Max Act: 0.6245. Min Act: -0.0000

Data Index: 1014715 (C4 (Web Text))

Max Activating Token Index: 761

Text #1

Max Range: 0.6245. Min Range: -0.6245

Max Act: 0.5892. Min Act: -0.0000

Data Index: 296018 (C4 (Web Text))

Max Activating Token Index: 719

Text #2

Max Range: 0.6245. Min Range: -0.6245

Max Act: 0.5481. Min Act: -0.0000

Data Index: 207059 (C4 (Web Text))

Max Activating Token Index: 652

Text #3

Max Range: 0.6245. Min Range: -0.6245

Max Act: 0.5318. Min Act: -0.0000

Data Index: 1012645 (C4 (Web Text))

Max Activating Token Index: 435

Text #4

Max Range: 0.6245. Min Range: -0.6245

Max Act: 0.5703. Min Act: -0.0000

Data Index: 1058220 (C4 (Web Text))

Max Activating Token Index: 831

Text #5

Max Range: 0.6245. Min Range: -0.6245

Max Act: 0.4972. Min Act: -0.0000

Data Index: 861150 (C4 (Web Text))

Max Activating Token Index: 471

Text #6

Max Range: 0.6245. Min Range: -0.6245

Max Act: 0.4918. Min Act: -0.0000

Data Index: 651790 (C4 (Web Text))

Max Activating Token Index: 673

Text #7

Max Range: 0.6245. Min Range: -0.6245

Max Act: 0.4458. Min Act: -0.0000

Data Index: 1209947 (C4 (Web Text))

Max Activating Token Index: 492

Text #8

Max Range: 0.6245. Min Range: -0.6245

Max Act: 0.4690. Min Act: -0.0000

Data Index: 133535 (C4 (Web Text))

Max Activating Token Index: 158

Text #9

Max Range: 0.6245. Min Range: -0.6245

Max Act: 0.4054. Min Act: -0.0000

Data Index: 1003394 (C4 (Web Text))

Max Activating Token Index: 1000

Text #10

Max Range: 0.6245. Min Range: -0.6245

Max Act: 0.3992. Min Act: -0.0000

Data Index: 421355 (C4 (Web Text))

Max Activating Token Index: 758

Text #11

Max Range: 0.6245. Min Range: -0.6245

Max Act: 0.3890. Min Act: -0.0000

Data Index: 1121200 (C4 (Web Text))

Max Activating Token Index: 703

Text #12

Max Range: 0.6245. Min Range: -0.6245

Max Act: 0.3596. Min Act: -0.0000

Data Index: 73941 (C4 (Web Text))

Max Activating Token Index: 684

Text #13

Max Range: 0.6245. Min Range: -0.6245

Max Act: 0.3720. Min Act: -0.0000

Data Index: 547590 (C4 (Web Text))

Max Activating Token Index: 7

Text #14

Max Range: 0.6245. Min Range: -0.6245

Max Act: 0.3956. Min Act: -0.0000

Data Index: 373141 (C4 (Web Text))

Max Activating Token Index: 634

Text #15

Max Range: 0.6245. Min Range: -0.6245

Max Act: 0.3580. Min Act: -0.0000

Data Index: 513691 (C4 (Web Text))

Max Activating Token Index: 657

Text #16

Max Range: 0.6245. Min Range: -0.6245

Max Act: 0.3584. Min Act: -0.0000

Data Index: 1267451 (C4 (Web Text))

Max Activating Token Index: 139

Text #17

Max Range: 0.6245. Min Range: -0.6245

Max Act: 0.3380. Min Act: -0.0000

Data Index: 985250 (C4 (Web Text))

Max Activating Token Index: 470

Text #18

Max Range: 0.6245. Min Range: -0.6245

Max Act: 0.3491. Min Act: -0.0000

Data Index: 1239127 (C4 (Web Text))

Max Activating Token Index: 362

Text #19

Max Range: 0.6245. Min Range: -0.6245

Max Act: 0.3476. Min Act: -0.0000

Data Index: 280914 (C4 (Web Text))

Max Activating Token Index: 169