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

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

Neuron 518 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.2765. Min Range: -1.2765

Max Act: 1.2765. Min Act: -0.0001

Data Index: 252089 (C4 (Web Text))

Max Activating Token Index: 97

Text #1

Max Range: 1.2765. Min Range: -1.2765

Max Act: 1.2342. Min Act: -0.0001

Data Index: 146848 (C4 (Web Text))

Max Activating Token Index: 883

Text #2

Max Range: 1.2765. Min Range: -1.2765

Max Act: 1.1533. Min Act: -0.0001

Data Index: 703764 (C4 (Web Text))

Max Activating Token Index: 361

Text #3

Max Range: 1.2765. Min Range: -1.2765

Max Act: 1.0033. Min Act: -0.0000

Data Index: 488010 (C4 (Web Text))

Max Activating Token Index: 601

Text #4

Max Range: 1.2765. Min Range: -1.2765

Max Act: 1.0738. Min Act: -0.0001

Data Index: 502944 (C4 (Web Text))

Max Activating Token Index: 751

Text #5

Max Range: 1.2765. Min Range: -1.2765

Max Act: 1.0147. Min Act: -0.0000

Data Index: 773066 (C4 (Web Text))

Max Activating Token Index: 987

Text #6

Max Range: 1.2765. Min Range: -1.2765

Max Act: 1.0352. Min Act: -0.0001

Data Index: 631983 (C4 (Web Text))

Max Activating Token Index: 542

Text #7

Max Range: 1.2765. Min Range: -1.2765

Max Act: 0.8378. Min Act: -0.0001

Data Index: 364770 (C4 (Web Text))

Max Activating Token Index: 699

Text #8

Max Range: 1.2765. Min Range: -1.2765

Max Act: 0.9686. Min Act: -0.0000

Data Index: 1185194 (C4 (Web Text))

Max Activating Token Index: 986

Text #9

Max Range: 1.2765. Min Range: -1.2765

Max Act: 0.9853. Min Act: -0.0001

Data Index: 840108 (C4 (Web Text))

Max Activating Token Index: 747

Text #10

Max Range: 1.2765. Min Range: -1.2765

Max Act: 0.9757. Min Act: -0.0000

Data Index: 1041017 (C4 (Web Text))

Max Activating Token Index: 935

Text #11

Max Range: 1.2765. Min Range: -1.2765

Max Act: 0.9719. Min Act: -0.0000

Data Index: 612977 (C4 (Web Text))

Max Activating Token Index: 210

Text #12

Max Range: 1.2765. Min Range: -1.2765

Max Act: 0.9224. Min Act: -0.0000

Data Index: 835917 (C4 (Web Text))

Max Activating Token Index: 467

Text #13

Max Range: 1.2765. Min Range: -1.2765

Max Act: 0.9570. Min Act: -0.0000

Data Index: 821734 (C4 (Web Text))

Max Activating Token Index: 873

Text #14

Max Range: 1.2765. Min Range: -1.2765

Max Act: 0.9515. Min Act: -0.0000

Data Index: 350239 (C4 (Web Text))

Max Activating Token Index: 889

Text #15

Max Range: 1.2765. Min Range: -1.2765

Max Act: 0.9338. Min Act: -0.0001

Data Index: 591164 (C4 (Web Text))

Max Activating Token Index: 592

Text #16

Max Range: 1.2765. Min Range: -1.2765

Max Act: 0.9284. Min Act: -0.0000

Data Index: 80392 (C4 (Web Text))

Max Activating Token Index: 52

Text #17

Max Range: 1.2765. Min Range: -1.2765

Max Act: 0.9328. Min Act: -0.0001

Data Index: 115776 (C4 (Web Text))

Max Activating Token Index: 796

Text #18

Max Range: 1.2765. Min Range: -1.2765

Max Act: 0.9493. Min Act: -0.0001

Data Index: 557853 (C4 (Web Text))

Max Activating Token Index: 347

Text #19

Max Range: 1.2765. Min Range: -1.2765

Max Act: 0.8749. Min Act: -0.0000

Data Index: 1111188 (C4 (Web Text))

Max Activating Token Index: 881