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

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

Neuron 2722 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7108. Min Range: -0.7108

Max Act: 0.7108. Min Act: 0.0000

Data Index: 311086 (C4 (Web Text))

Max Activating Token Index: 298

Text #1

Max Range: 0.7108. Min Range: -0.7108

Max Act: 0.5610. Min Act: -0.0000

Data Index: 983305 (C4 (Web Text))

Max Activating Token Index: 638

Text #2

Max Range: 0.7108. Min Range: -0.7108

Max Act: 0.5553. Min Act: -0.0000

Data Index: 963316 (C4 (Web Text))

Max Activating Token Index: 474

Text #3

Max Range: 0.7108. Min Range: -0.7108

Max Act: 0.5741. Min Act: -0.0000

Data Index: 788635 (C4 (Web Text))

Max Activating Token Index: 494

Text #4

Max Range: 0.7108. Min Range: -0.7108

Max Act: 0.5181. Min Act: -0.0000

Data Index: 942245 (C4 (Web Text))

Max Activating Token Index: 480

Text #5

Max Range: 0.7108. Min Range: -0.7108

Max Act: 0.5431. Min Act: -0.0000

Data Index: 630772 (C4 (Web Text))

Max Activating Token Index: 980

Text #6

Max Range: 0.7108. Min Range: -0.7108

Max Act: 0.4895. Min Act: -0.0000

Data Index: 758479 (C4 (Web Text))

Max Activating Token Index: 898

Text #7

Max Range: 0.7108. Min Range: -0.7108

Max Act: 0.5239. Min Act: -0.0000

Data Index: 1211515 (C4 (Web Text))

Max Activating Token Index: 663

Text #8

Max Range: 0.7108. Min Range: -0.7108

Max Act: 0.5073. Min Act: -0.0000

Data Index: 21431 (C4 (Web Text))

Max Activating Token Index: 202

Text #9

Max Range: 0.7108. Min Range: -0.7108

Max Act: 0.4977. Min Act: -0.0000

Data Index: 1086954 (C4 (Web Text))

Max Activating Token Index: 924

Text #10

Max Range: 0.7108. Min Range: -0.7108

Max Act: 0.4970. Min Act: -0.0000

Data Index: 1223654 (C4 (Web Text))

Max Activating Token Index: 546

Text #11

Max Range: 0.7108. Min Range: -0.7108

Max Act: 0.4952. Min Act: -0.0000

Data Index: 184602 (C4 (Web Text))

Max Activating Token Index: 478

Text #12

Max Range: 0.7108. Min Range: -0.7108

Max Act: 0.5042. Min Act: -0.0000

Data Index: 191070 (C4 (Web Text))

Max Activating Token Index: 529

Text #13

Max Range: 0.7108. Min Range: -0.7108

Max Act: 0.4865. Min Act: -0.0000

Data Index: 655702 (C4 (Web Text))

Max Activating Token Index: 558

Text #14

Max Range: 0.7108. Min Range: -0.7108

Max Act: 0.4732. Min Act: -0.0000

Data Index: 724819 (C4 (Web Text))

Max Activating Token Index: 209

Text #15

Max Range: 0.7108. Min Range: -0.7108

Max Act: 0.4790. Min Act: -0.0000

Data Index: 570967 (C4 (Web Text))

Max Activating Token Index: 273

Text #16

Max Range: 0.7108. Min Range: -0.7108

Max Act: 0.4794. Min Act: -0.0000

Data Index: 24141 (C4 (Web Text))

Max Activating Token Index: 364

Text #17

Max Range: 0.7108. Min Range: -0.7108

Max Act: 0.4926. Min Act: -0.0000

Data Index: 171210 (C4 (Web Text))

Max Activating Token Index: 711

Text #18

Max Range: 0.7108. Min Range: -0.7108

Max Act: 0.4593. Min Act: -0.0000

Data Index: 710472 (C4 (Web Text))

Max Activating Token Index: 663

Text #19

Max Range: 0.7108. Min Range: -0.7108

Max Act: 0.4760. Min Act: -0.0000

Data Index: 583287 (C4 (Web Text))

Max Activating Token Index: 90