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

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

Neuron 2323 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.6072. Min Range: -2.6072

Max Act: 2.5726. Min Act: -0.0000

Data Index: 1299109 (C4 (Web Text))

Max Activating Token Index: 826

Text #1

Max Range: 2.6072. Min Range: -2.6072

Max Act: 2.4827. Min Act: -0.0000

Data Index: 625034 (C4 (Web Text))

Max Activating Token Index: 904

Text #2

Max Range: 2.6072. Min Range: -2.6072

Max Act: 2.6072. Min Act: -0.0000

Data Index: 690316 (C4 (Web Text))

Max Activating Token Index: 54

Text #3

Max Range: 2.6072. Min Range: -2.6072

Max Act: 2.2655. Min Act: -0.0000

Data Index: 65752 (C4 (Web Text))

Max Activating Token Index: 162

Text #4

Max Range: 2.6072. Min Range: -2.6072

Max Act: 2.3854. Min Act: -0.0000

Data Index: 803647 (C4 (Web Text))

Max Activating Token Index: 624

Text #5

Max Range: 2.6072. Min Range: -2.6072

Max Act: 2.3373. Min Act: -0.0000

Data Index: 1152221 (C4 (Web Text))

Max Activating Token Index: 221

Text #6

Max Range: 2.6072. Min Range: -2.6072

Max Act: 2.1987. Min Act: -0.0000

Data Index: 1241321 (C4 (Web Text))

Max Activating Token Index: 53

Text #7

Max Range: 2.6072. Min Range: -2.6072

Max Act: 2.0562. Min Act: -0.0000

Data Index: 1201956 (C4 (Web Text))

Max Activating Token Index: 707

Text #8

Max Range: 2.6072. Min Range: -2.6072

Max Act: 2.2352. Min Act: -0.0000

Data Index: 56727 (C4 (Web Text))

Max Activating Token Index: 99

Text #9

Max Range: 2.6072. Min Range: -2.6072

Max Act: 2.2042. Min Act: -0.0000

Data Index: 1216739 (C4 (Web Text))

Max Activating Token Index: 951

Text #10

Max Range: 2.6072. Min Range: -2.6072

Max Act: 1.9832. Min Act: -0.0000

Data Index: 1052910 (C4 (Web Text))

Max Activating Token Index: 308

Text #11

Max Range: 2.6072. Min Range: -2.6072

Max Act: 1.8531. Min Act: -0.0000

Data Index: 851704 (C4 (Web Text))

Max Activating Token Index: 488

Text #12

Max Range: 2.6072. Min Range: -2.6072

Max Act: 1.9332. Min Act: -0.0000

Data Index: 496551 (C4 (Web Text))

Max Activating Token Index: 66

Text #13

Max Range: 2.6072. Min Range: -2.6072

Max Act: 1.7104. Min Act: -0.0000

Data Index: 1065270 (C4 (Web Text))

Max Activating Token Index: 788

Text #14

Max Range: 2.6072. Min Range: -2.6072

Max Act: 1.9141. Min Act: -0.0000

Data Index: 1256856 (C4 (Web Text))

Max Activating Token Index: 457

Text #15

Max Range: 2.6072. Min Range: -2.6072

Max Act: 1.7509. Min Act: -0.0000

Data Index: 378661 (C4 (Web Text))

Max Activating Token Index: 513

Text #16

Max Range: 2.6072. Min Range: -2.6072

Max Act: 1.5581. Min Act: -0.0000

Data Index: 530543 (C4 (Web Text))

Max Activating Token Index: 330

Text #17

Max Range: 2.6072. Min Range: -2.6072

Max Act: 1.7116. Min Act: -0.0000

Data Index: 708535 (C4 (Web Text))

Max Activating Token Index: 786

Text #18

Max Range: 2.6072. Min Range: -2.6072

Max Act: 1.5969. Min Act: -0.0000

Data Index: 748525 (C4 (Web Text))

Max Activating Token Index: 351

Text #19

Max Range: 2.6072. Min Range: -2.6072

Max Act: 1.4845. Min Act: -0.0000

Data Index: 190936 (C4 (Web Text))

Max Activating Token Index: 977