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

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

Neuron 1424 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7741. Min Range: -0.7741

Max Act: 0.7741. Min Act: -0.0000

Data Index: 103094 (C4 (Web Text))

Max Activating Token Index: 587

Text #1

Max Range: 0.7741. Min Range: -0.7741

Max Act: 0.6976. Min Act: -0.0000

Data Index: 1063874 (C4 (Web Text))

Max Activating Token Index: 494

Text #2

Max Range: 0.7741. Min Range: -0.7741

Max Act: 0.6753. Min Act: -0.0000

Data Index: 1037736 (C4 (Web Text))

Max Activating Token Index: 36

Text #3

Max Range: 0.7741. Min Range: -0.7741

Max Act: 0.6607. Min Act: 0.0000

Data Index: 1271159 (C4 (Web Text))

Max Activating Token Index: 584

Text #4

Max Range: 0.7741. Min Range: -0.7741

Max Act: 0.6573. Min Act: 0.0000

Data Index: 1159778 (C4 (Web Text))

Max Activating Token Index: 269

Text #5

Max Range: 0.7741. Min Range: -0.7741

Max Act: 0.6920. Min Act: -0.0000

Data Index: 674047 (C4 (Web Text))

Max Activating Token Index: 936

Text #6

Max Range: 0.7741. Min Range: -0.7741

Max Act: 0.6596. Min Act: -0.0000

Data Index: 584746 (C4 (Web Text))

Max Activating Token Index: 1022

Text #7

Max Range: 0.7741. Min Range: -0.7741

Max Act: 0.5962. Min Act: -0.0000

Data Index: 876082 (C4 (Web Text))

Max Activating Token Index: 727

Text #8

Max Range: 0.7741. Min Range: -0.7741

Max Act: 0.6116. Min Act: 0.0000

Data Index: 633017 (C4 (Web Text))

Max Activating Token Index: 135

Text #9

Max Range: 0.7741. Min Range: -0.7741

Max Act: 0.6101. Min Act: -0.0000

Data Index: 694864 (C4 (Web Text))

Max Activating Token Index: 515

Text #10

Max Range: 0.7741. Min Range: -0.7741

Max Act: 0.6098. Min Act: -0.0000

Data Index: 718809 (C4 (Web Text))

Max Activating Token Index: 369

Text #11

Max Range: 0.7741. Min Range: -0.7741

Max Act: 0.6233. Min Act: -0.0000

Data Index: 720490 (C4 (Web Text))

Max Activating Token Index: 808

Text #12

Max Range: 0.7741. Min Range: -0.7741

Max Act: 0.6279. Min Act: -0.0000

Data Index: 721628 (C4 (Web Text))

Max Activating Token Index: 83

Text #13

Max Range: 0.7741. Min Range: -0.7741

Max Act: 0.6089. Min Act: -0.0000

Data Index: 378461 (C4 (Web Text))

Max Activating Token Index: 107

Text #14

Max Range: 0.7741. Min Range: -0.7741

Max Act: 0.6269. Min Act: 0.0006

Data Index: 911800 (C4 (Web Text))

Max Activating Token Index: 895

Text #15

Max Range: 0.7741. Min Range: -0.7741

Max Act: 0.6069. Min Act: -0.0000

Data Index: 357044 (C4 (Web Text))

Max Activating Token Index: 314

Text #16

Max Range: 0.7741. Min Range: -0.7741

Max Act: 0.5979. Min Act: -0.0000

Data Index: 58073 (C4 (Web Text))

Max Activating Token Index: 805

Text #17

Max Range: 0.7741. Min Range: -0.7741

Max Act: 0.5846. Min Act: 0.0000

Data Index: 1089792 (C4 (Web Text))

Max Activating Token Index: 347

Text #18

Max Range: 0.7741. Min Range: -0.7741

Max Act: 0.5980. Min Act: -0.0000

Data Index: 405374 (C4 (Web Text))

Max Activating Token Index: 552

Text #19

Max Range: 0.7741. Min Range: -0.7741

Max Act: 0.5904. Min Act: 0.0000

Data Index: 554684 (C4 (Web Text))

Max Activating Token Index: 28