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

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

Neuron 620 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6965. Min Range: -1.6965

Max Act: 1.6880. Min Act: -0.0000

Data Index: 717060 (C4 (Web Text))

Max Activating Token Index: 726

Text #1

Max Range: 1.6965. Min Range: -1.6965

Max Act: 1.6965. Min Act: -0.0001

Data Index: 347361 (C4 (Web Text))

Max Activating Token Index: 540

Text #2

Max Range: 1.6965. Min Range: -1.6965

Max Act: 1.3470. Min Act: -0.0000

Data Index: 238024 (C4 (Web Text))

Max Activating Token Index: 216

Text #3

Max Range: 1.6965. Min Range: -1.6965

Max Act: 1.1085. Min Act: -0.0001

Data Index: 299779 (C4 (Web Text))

Max Activating Token Index: 763

Text #4

Max Range: 1.6965. Min Range: -1.6965

Max Act: 1.2978. Min Act: -0.0000

Data Index: 1067838 (C4 (Web Text))

Max Activating Token Index: 1014

Text #5

Max Range: 1.6965. Min Range: -1.6965

Max Act: 1.3800. Min Act: -0.0001

Data Index: 407397 (C4 (Web Text))

Max Activating Token Index: 946

Text #6

Max Range: 1.6965. Min Range: -1.6965

Max Act: 1.1949. Min Act: -0.0000

Data Index: 709014 (C4 (Web Text))

Max Activating Token Index: 837

Text #7

Max Range: 1.6965. Min Range: -1.6965

Max Act: 1.2638. Min Act: -0.0001

Data Index: 1056156 (C4 (Web Text))

Max Activating Token Index: 546

Text #8

Max Range: 1.6965. Min Range: -1.6965

Max Act: 1.1477. Min Act: -0.0001

Data Index: 1306170 (C4 (Web Text))

Max Activating Token Index: 474

Text #9

Max Range: 1.6965. Min Range: -1.6965

Max Act: 1.1860. Min Act: -0.0000

Data Index: 106801 (C4 (Web Text))

Max Activating Token Index: 682

Text #10

Max Range: 1.6965. Min Range: -1.6965

Max Act: 1.1033. Min Act: -0.0001

Data Index: 788142 (C4 (Web Text))

Max Activating Token Index: 1009

Text #11

Max Range: 1.6965. Min Range: -1.6965

Max Act: 1.1818. Min Act: -0.0000

Data Index: 756714 (C4 (Web Text))

Max Activating Token Index: 1008

Text #12

Max Range: 1.6965. Min Range: -1.6965

Max Act: 1.1844. Min Act: -0.0001

Data Index: 24993 (C4 (Web Text))

Max Activating Token Index: 578

Text #13

Max Range: 1.6965. Min Range: -1.6965

Max Act: 1.1662. Min Act: -0.0000

Data Index: 410040 (C4 (Web Text))

Max Activating Token Index: 616

Text #14

Max Range: 1.6965. Min Range: -1.6965

Max Act: 1.1116. Min Act: -0.0000

Data Index: 680354 (C4 (Web Text))

Max Activating Token Index: 854

Text #15

Max Range: 1.6965. Min Range: -1.6965

Max Act: 1.1877. Min Act: -0.0000

Data Index: 31700 (C4 (Web Text))

Max Activating Token Index: 958

Text #16

Max Range: 1.6965. Min Range: -1.6965

Max Act: 1.1200. Min Act: -0.0001

Data Index: 1306687 (C4 (Web Text))

Max Activating Token Index: 893

Text #17

Max Range: 1.6965. Min Range: -1.6965

Max Act: 1.1135. Min Act: -0.0000

Data Index: 1061749 (C4 (Web Text))

Max Activating Token Index: 929

Text #18

Max Range: 1.6965. Min Range: -1.6965

Max Act: 0.9809. Min Act: -0.0000

Data Index: 1389068 (Python Code)

Max Activating Token Index: 708

Text #19

Max Range: 1.6965. Min Range: -1.6965

Max Act: 1.0643. Min Act: -0.0001

Data Index: 939349 (C4 (Web Text))

Max Activating Token Index: 992