Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 770 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.7729. Min Range: -0.7729

Max Act: 0.7729. Min Act: -0.0000

Data Index: 327623 (C4 (Web Text))

Max Activating Token Index: 610

Text #1

Max Range: 0.7729. Min Range: -0.7729

Max Act: 0.7028. Min Act: -0.0000

Data Index: 520659 (C4 (Web Text))

Max Activating Token Index: 441

Text #2

Max Range: 0.7729. Min Range: -0.7729

Max Act: 0.6649. Min Act: -0.0000

Data Index: 219581 (C4 (Web Text))

Max Activating Token Index: 413

Text #3

Max Range: 0.7729. Min Range: -0.7729

Max Act: 0.5820. Min Act: -0.0000

Data Index: 343762 (C4 (Web Text))

Max Activating Token Index: 558

Text #4

Max Range: 0.7729. Min Range: -0.7729

Max Act: 0.5297. Min Act: -0.0000

Data Index: 1326224 (C4 (Web Text))

Max Activating Token Index: 405

Text #5

Max Range: 0.7729. Min Range: -0.7729

Max Act: 0.5008. Min Act: -0.0000

Data Index: 1177428 (C4 (Web Text))

Max Activating Token Index: 768

Text #6

Max Range: 0.7729. Min Range: -0.7729

Max Act: 0.5844. Min Act: -0.0000

Data Index: 680004 (C4 (Web Text))

Max Activating Token Index: 858

Text #7

Max Range: 0.7729. Min Range: -0.7729

Max Act: 0.4813. Min Act: -0.0000

Data Index: 457706 (C4 (Web Text))

Max Activating Token Index: 740

Text #8

Max Range: 0.7729. Min Range: -0.7729

Max Act: 0.5419. Min Act: -0.0000

Data Index: 1210854 (C4 (Web Text))

Max Activating Token Index: 871

Text #9

Max Range: 0.7729. Min Range: -0.7729

Max Act: 0.4648. Min Act: -0.0000

Data Index: 952020 (C4 (Web Text))

Max Activating Token Index: 149

Text #10

Max Range: 0.7729. Min Range: -0.7729

Max Act: 0.4930. Min Act: -0.0000

Data Index: 260283 (C4 (Web Text))

Max Activating Token Index: 1022

Text #11

Max Range: 0.7729. Min Range: -0.7729

Max Act: 0.4562. Min Act: -0.0000

Data Index: 360111 (C4 (Web Text))

Max Activating Token Index: 168

Text #12

Max Range: 0.7729. Min Range: -0.7729

Max Act: 0.4661. Min Act: -0.0000

Data Index: 1058177 (C4 (Web Text))

Max Activating Token Index: 300

Text #13

Max Range: 0.7729. Min Range: -0.7729

Max Act: 0.4951. Min Act: -0.0000

Data Index: 78109 (C4 (Web Text))

Max Activating Token Index: 900

Text #14

Max Range: 0.7729. Min Range: -0.7729

Max Act: 0.4465. Min Act: -0.0000

Data Index: 599284 (C4 (Web Text))

Max Activating Token Index: 787

Text #15

Max Range: 0.7729. Min Range: -0.7729

Max Act: 0.4532. Min Act: -0.0000

Data Index: 1193996 (C4 (Web Text))

Max Activating Token Index: 598

Text #16

Max Range: 0.7729. Min Range: -0.7729

Max Act: 0.4544. Min Act: -0.0000

Data Index: 377501 (C4 (Web Text))

Max Activating Token Index: 63

Text #17

Max Range: 0.7729. Min Range: -0.7729

Max Act: 0.4661. Min Act: -0.0000

Data Index: 1170723 (C4 (Web Text))

Max Activating Token Index: 963

Text #18

Max Range: 0.7729. Min Range: -0.7729

Max Act: 0.4681. Min Act: -0.0000

Data Index: 830652 (C4 (Web Text))

Max Activating Token Index: 609

Text #19

Max Range: 0.7729. Min Range: -0.7729

Max Act: 0.5099. Min Act: -0.0000

Data Index: 744836 (C4 (Web Text))

Max Activating Token Index: 763