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

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

Neuron 5461 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4792. Min Range: -2.4792

Max Act: 2.2592. Min Act: -0.0000

Data Index: 1254227 (C4 (Web Text))

Max Activating Token Index: 105

Text #1

Max Range: 2.4792. Min Range: -2.4792

Max Act: 2.4792. Min Act: -0.0000

Data Index: 1342978 (C4 (Web Text))

Max Activating Token Index: 931

Text #2

Max Range: 2.4792. Min Range: -2.4792

Max Act: 1.9966. Min Act: -0.0000

Data Index: 1161643 (C4 (Web Text))

Max Activating Token Index: 589

Text #3

Max Range: 2.4792. Min Range: -2.4792

Max Act: 1.9189. Min Act: -0.0000

Data Index: 255120 (C4 (Web Text))

Max Activating Token Index: 413

Text #4

Max Range: 2.4792. Min Range: -2.4792

Max Act: 1.9800. Min Act: -0.0000

Data Index: 240173 (C4 (Web Text))

Max Activating Token Index: 844

Text #5

Max Range: 2.4792. Min Range: -2.4792

Max Act: 2.4164. Min Act: -0.0000

Data Index: 967920 (C4 (Web Text))

Max Activating Token Index: 816

Text #6

Max Range: 2.4792. Min Range: -2.4792

Max Act: 1.8402. Min Act: -0.0000

Data Index: 267095 (C4 (Web Text))

Max Activating Token Index: 45

Text #7

Max Range: 2.4792. Min Range: -2.4792

Max Act: 1.7506. Min Act: -0.0000

Data Index: 1344458 (C4 (Web Text))

Max Activating Token Index: 53

Text #8

Max Range: 2.4792. Min Range: -2.4792

Max Act: 1.5816. Min Act: -0.0000

Data Index: 92791 (C4 (Web Text))

Max Activating Token Index: 695

Text #9

Max Range: 2.4792. Min Range: -2.4792

Max Act: 1.8611. Min Act: -0.0000

Data Index: 745906 (C4 (Web Text))

Max Activating Token Index: 927

Text #10

Max Range: 2.4792. Min Range: -2.4792

Max Act: 1.6840. Min Act: -0.0000

Data Index: 635816 (C4 (Web Text))

Max Activating Token Index: 924

Text #11

Max Range: 2.4792. Min Range: -2.4792

Max Act: 1.5601. Min Act: -0.0000

Data Index: 1065896 (C4 (Web Text))

Max Activating Token Index: 455

Text #12

Max Range: 2.4792. Min Range: -2.4792

Max Act: 1.5134. Min Act: -0.0000

Data Index: 1230931 (C4 (Web Text))

Max Activating Token Index: 328

Text #13

Max Range: 2.4792. Min Range: -2.4792

Max Act: 1.5679. Min Act: -0.0000

Data Index: 196286 (C4 (Web Text))

Max Activating Token Index: 728

Text #14

Max Range: 2.4792. Min Range: -2.4792

Max Act: 1.5643. Min Act: -0.0000

Data Index: 103763 (C4 (Web Text))

Max Activating Token Index: 347

Text #15

Max Range: 2.4792. Min Range: -2.4792

Max Act: 1.6473. Min Act: -0.0000

Data Index: 834873 (C4 (Web Text))

Max Activating Token Index: 257

Text #16

Max Range: 2.4792. Min Range: -2.4792

Max Act: 1.5413. Min Act: -0.0000

Data Index: 1106280 (C4 (Web Text))

Max Activating Token Index: 828

Text #17

Max Range: 2.4792. Min Range: -2.4792

Max Act: 1.4053. Min Act: -0.0000

Data Index: 360972 (C4 (Web Text))

Max Activating Token Index: 175

Text #18

Max Range: 2.4792. Min Range: -2.4792

Max Act: 1.4691. Min Act: -0.0000

Data Index: 40573 (C4 (Web Text))

Max Activating Token Index: 511

Text #19

Max Range: 2.4792. Min Range: -2.4792

Max Act: 1.4675. Min Act: -0.0000

Data Index: 49943 (C4 (Web Text))

Max Activating Token Index: 917