Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2915 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.4827. Min Range: -1.4827

Max Act: 1.4827. Min Act: -0.0000

Data Index: 276040 (C4 (Web Text))

Max Activating Token Index: 386

Text #1

Max Range: 1.4827. Min Range: -1.4827

Max Act: 1.4343. Min Act: -0.0000

Data Index: 533952 (C4 (Web Text))

Max Activating Token Index: 509

Text #2

Max Range: 1.4827. Min Range: -1.4827

Max Act: 1.3777. Min Act: -0.0000

Data Index: 1130777 (C4 (Web Text))

Max Activating Token Index: 176

Text #3

Max Range: 1.4827. Min Range: -1.4827

Max Act: 1.3273. Min Act: -0.0000

Data Index: 1179894 (C4 (Web Text))

Max Activating Token Index: 293

Text #4

Max Range: 1.4827. Min Range: -1.4827

Max Act: 1.3651. Min Act: -0.0001

Data Index: 983503 (C4 (Web Text))

Max Activating Token Index: 731

Text #5

Max Range: 1.4827. Min Range: -1.4827

Max Act: 1.3237. Min Act: -0.0000

Data Index: 485904 (C4 (Web Text))

Max Activating Token Index: 557

Text #6

Max Range: 1.4827. Min Range: -1.4827

Max Act: 1.3095. Min Act: -0.0000

Data Index: 890387 (C4 (Web Text))

Max Activating Token Index: 430

Text #7

Max Range: 1.4827. Min Range: -1.4827

Max Act: 1.2875. Min Act: -0.0000

Data Index: 569202 (C4 (Web Text))

Max Activating Token Index: 331

Text #8

Max Range: 1.4827. Min Range: -1.4827

Max Act: 1.2859. Min Act: -0.0001

Data Index: 1108206 (C4 (Web Text))

Max Activating Token Index: 480

Text #9

Max Range: 1.4827. Min Range: -1.4827

Max Act: 1.2457. Min Act: -0.0000

Data Index: 588789 (C4 (Web Text))

Max Activating Token Index: 98

Text #10

Max Range: 1.4827. Min Range: -1.4827

Max Act: 1.2387. Min Act: -0.0000

Data Index: 316925 (C4 (Web Text))

Max Activating Token Index: 516

Text #11

Max Range: 1.4827. Min Range: -1.4827

Max Act: 1.2832. Min Act: -0.0000

Data Index: 895958 (C4 (Web Text))

Max Activating Token Index: 467

Text #12

Max Range: 1.4827. Min Range: -1.4827

Max Act: 1.2357. Min Act: -0.0000

Data Index: 1557502 (Python Code)

Max Activating Token Index: 14

Text #13

Max Range: 1.4827. Min Range: -1.4827

Max Act: 1.2007. Min Act: -0.0000

Data Index: 266290 (C4 (Web Text))

Max Activating Token Index: 73

Text #14

Max Range: 1.4827. Min Range: -1.4827

Max Act: 1.2316. Min Act: -0.0000

Data Index: 231986 (C4 (Web Text))

Max Activating Token Index: 640

Text #15

Max Range: 1.4827. Min Range: -1.4827

Max Act: 1.1456. Min Act: -0.0000

Data Index: 34339 (C4 (Web Text))

Max Activating Token Index: 877

Text #16

Max Range: 1.4827. Min Range: -1.4827

Max Act: 1.1715. Min Act: -0.0000

Data Index: 767949 (C4 (Web Text))

Max Activating Token Index: 491

Text #17

Max Range: 1.4827. Min Range: -1.4827

Max Act: 1.2111. Min Act: -0.0000

Data Index: 532019 (C4 (Web Text))

Max Activating Token Index: 518

Text #18

Max Range: 1.4827. Min Range: -1.4827

Max Act: 1.1634. Min Act: -0.0000

Data Index: 216935 (C4 (Web Text))

Max Activating Token Index: 196

Text #19

Max Range: 1.4827. Min Range: -1.4827

Max Act: 1.1820. Min Act: -0.0000

Data Index: 623615 (C4 (Web Text))

Max Activating Token Index: 85