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

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

Neuron 3816 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6521. Min Range: -1.6521

Max Act: 1.6521. Min Act: -0.0001

Data Index: 214689 (C4 (Web Text))

Max Activating Token Index: 763

Text #1

Max Range: 1.6521. Min Range: -1.6521

Max Act: 0.9518. Min Act: -0.0001

Data Index: 1295122 (C4 (Web Text))

Max Activating Token Index: 454

Text #2

Max Range: 1.6521. Min Range: -1.6521

Max Act: 0.9090. Min Act: -0.0000

Data Index: 357007 (C4 (Web Text))

Max Activating Token Index: 561

Text #3

Max Range: 1.6521. Min Range: -1.6521

Max Act: 0.9084. Min Act: -0.0000

Data Index: 708299 (C4 (Web Text))

Max Activating Token Index: 619

Text #4

Max Range: 1.6521. Min Range: -1.6521

Max Act: 0.8498. Min Act: -0.0000

Data Index: 13412 (C4 (Web Text))

Max Activating Token Index: 673

Text #5

Max Range: 1.6521. Min Range: -1.6521

Max Act: 0.7005. Min Act: -0.0000

Data Index: 1170134 (C4 (Web Text))

Max Activating Token Index: 559

Text #6

Max Range: 1.6521. Min Range: -1.6521

Max Act: 0.6524. Min Act: -0.0000

Data Index: 1259237 (C4 (Web Text))

Max Activating Token Index: 951

Text #7

Max Range: 1.6521. Min Range: -1.6521

Max Act: 0.5995. Min Act: -0.0001

Data Index: 640505 (C4 (Web Text))

Max Activating Token Index: 463

Text #8

Max Range: 1.6521. Min Range: -1.6521

Max Act: 0.5874. Min Act: -0.0000

Data Index: 114894 (C4 (Web Text))

Max Activating Token Index: 826

Text #9

Max Range: 1.6521. Min Range: -1.6521

Max Act: 0.6711. Min Act: -0.0000

Data Index: 580916 (C4 (Web Text))

Max Activating Token Index: 952

Text #10

Max Range: 1.6521. Min Range: -1.6521

Max Act: 0.4461. Min Act: -0.0000

Data Index: 1075144 (C4 (Web Text))

Max Activating Token Index: 256

Text #11

Max Range: 1.6521. Min Range: -1.6521

Max Act: 0.4256. Min Act: -0.0000

Data Index: 684579 (C4 (Web Text))

Max Activating Token Index: 949

Text #12

Max Range: 1.6521. Min Range: -1.6521

Max Act: 0.4130. Min Act: -0.0000

Data Index: 1137166 (C4 (Web Text))

Max Activating Token Index: 96

Text #13

Max Range: 1.6521. Min Range: -1.6521

Max Act: 0.3608. Min Act: -0.0000

Data Index: 1222787 (C4 (Web Text))

Max Activating Token Index: 376

Text #14

Max Range: 1.6521. Min Range: -1.6521

Max Act: 0.3979. Min Act: -0.0001

Data Index: 1179547 (C4 (Web Text))

Max Activating Token Index: 209

Text #15

Max Range: 1.6521. Min Range: -1.6521

Max Act: 0.3677. Min Act: -0.0001

Data Index: 914982 (C4 (Web Text))

Max Activating Token Index: 546

Text #16

Max Range: 1.6521. Min Range: -1.6521

Max Act: 0.3674. Min Act: -0.0000

Data Index: 1257908 (C4 (Web Text))

Max Activating Token Index: 551

Text #17

Max Range: 1.6521. Min Range: -1.6521

Max Act: 0.3170. Min Act: -0.0000

Data Index: 97492 (C4 (Web Text))

Max Activating Token Index: 341

Text #18

Max Range: 1.6521. Min Range: -1.6521

Max Act: 0.3331. Min Act: -0.0001

Data Index: 1197066 (C4 (Web Text))

Max Activating Token Index: 918

Text #19

Max Range: 1.6521. Min Range: -1.6521

Max Act: 0.3009. Min Act: -0.0001

Data Index: 786932 (C4 (Web Text))

Max Activating Token Index: 753