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

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

Neuron 1391 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2666. Min Range: -0.2666

Max Act: 0.2666. Min Act: -0.0000

Data Index: 770760 (C4 (Web Text))

Max Activating Token Index: 752

Text #1

Max Range: 0.2666. Min Range: -0.2666

Max Act: 0.2508. Min Act: -0.0001

Data Index: 150479 (C4 (Web Text))

Max Activating Token Index: 191

Text #2

Max Range: 0.2666. Min Range: -0.2666

Max Act: 0.2480. Min Act: -0.0000

Data Index: 449435 (C4 (Web Text))

Max Activating Token Index: 867

Text #3

Max Range: 0.2666. Min Range: -0.2666

Max Act: 0.2393. Min Act: -0.0001

Data Index: 1157905 (C4 (Web Text))

Max Activating Token Index: 178

Text #4

Max Range: 0.2666. Min Range: -0.2666

Max Act: 0.2205. Min Act: -0.0000

Data Index: 1027721 (C4 (Web Text))

Max Activating Token Index: 936

Text #5

Max Range: 0.2666. Min Range: -0.2666

Max Act: 0.2430. Min Act: -0.0000

Data Index: 340578 (C4 (Web Text))

Max Activating Token Index: 469

Text #6

Max Range: 0.2666. Min Range: -0.2666

Max Act: 0.2170. Min Act: -0.0001

Data Index: 30911 (C4 (Web Text))

Max Activating Token Index: 322

Text #7

Max Range: 0.2666. Min Range: -0.2666

Max Act: 0.2244. Min Act: -0.0001

Data Index: 1364757 (Python Code)

Max Activating Token Index: 870

Text #8

Max Range: 0.2666. Min Range: -0.2666

Max Act: 0.2267. Min Act: -0.0001

Data Index: 1132861 (C4 (Web Text))

Max Activating Token Index: 661

Text #9

Max Range: 0.2666. Min Range: -0.2666

Max Act: 0.2105. Min Act: -0.0000

Data Index: 200862 (C4 (Web Text))

Max Activating Token Index: 710

Text #10

Max Range: 0.2666. Min Range: -0.2666

Max Act: 0.2106. Min Act: -0.0001

Data Index: 752730 (C4 (Web Text))

Max Activating Token Index: 601

Text #11

Max Range: 0.2666. Min Range: -0.2666

Max Act: 0.2085. Min Act: -0.0000

Data Index: 928025 (C4 (Web Text))

Max Activating Token Index: 377

Text #12

Max Range: 0.2666. Min Range: -0.2666

Max Act: 0.1996. Min Act: -0.0000

Data Index: 188083 (C4 (Web Text))

Max Activating Token Index: 24

Text #13

Max Range: 0.2666. Min Range: -0.2666

Max Act: 0.1974. Min Act: -0.0001

Data Index: 745345 (C4 (Web Text))

Max Activating Token Index: 958

Text #14

Max Range: 0.2666. Min Range: -0.2666

Max Act: 0.2098. Min Act: -0.0001

Data Index: 1291967 (C4 (Web Text))

Max Activating Token Index: 739

Text #15

Max Range: 0.2666. Min Range: -0.2666

Max Act: 0.1945. Min Act: -0.0000

Data Index: 563602 (C4 (Web Text))

Max Activating Token Index: 327

Text #16

Max Range: 0.2666. Min Range: -0.2666

Max Act: 0.1916. Min Act: -0.0001

Data Index: 299182 (C4 (Web Text))

Max Activating Token Index: 114

Text #17

Max Range: 0.2666. Min Range: -0.2666

Max Act: 0.1831. Min Act: -0.0000

Data Index: 485843 (C4 (Web Text))

Max Activating Token Index: 367

Text #18

Max Range: 0.2666. Min Range: -0.2666

Max Act: 0.1955. Min Act: -0.0001

Data Index: 868431 (C4 (Web Text))

Max Activating Token Index: 244

Text #19

Max Range: 0.2666. Min Range: -0.2666

Max Act: 0.1932. Min Act: -0.0000

Data Index: 715651 (C4 (Web Text))

Max Activating Token Index: 865