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

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

Neuron 2484 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3136. Min Range: -0.3136

Max Act: 0.2968. Min Act: -0.0000

Data Index: 288315 (C4 (Web Text))

Max Activating Token Index: 642

Text #1

Max Range: 0.3136. Min Range: -0.3136

Max Act: 0.2831. Min Act: -0.0000

Data Index: 827998 (C4 (Web Text))

Max Activating Token Index: 1006

Text #2

Max Range: 0.3136. Min Range: -0.3136

Max Act: 0.3038. Min Act: -0.0000

Data Index: 1152793 (C4 (Web Text))

Max Activating Token Index: 886

Text #3

Max Range: 0.3136. Min Range: -0.3136

Max Act: 0.3136. Min Act: -0.0000

Data Index: 1154905 (C4 (Web Text))

Max Activating Token Index: 952

Text #4

Max Range: 0.3136. Min Range: -0.3136

Max Act: 0.2925. Min Act: -0.0000

Data Index: 444803 (C4 (Web Text))

Max Activating Token Index: 4

Text #5

Max Range: 0.3136. Min Range: -0.3136

Max Act: 0.2920. Min Act: -0.0000

Data Index: 1035155 (C4 (Web Text))

Max Activating Token Index: 344

Text #6

Max Range: 0.3136. Min Range: -0.3136

Max Act: 0.2811. Min Act: -0.0000

Data Index: 984742 (C4 (Web Text))

Max Activating Token Index: 1001

Text #7

Max Range: 0.3136. Min Range: -0.3136

Max Act: 0.2289. Min Act: -0.0000

Data Index: 815537 (C4 (Web Text))

Max Activating Token Index: 296

Text #8

Max Range: 0.3136. Min Range: -0.3136

Max Act: 0.2644. Min Act: -0.0000

Data Index: 174407 (C4 (Web Text))

Max Activating Token Index: 915

Text #9

Max Range: 0.3136. Min Range: -0.3136

Max Act: 0.2511. Min Act: -0.0000

Data Index: 1054519 (C4 (Web Text))

Max Activating Token Index: 48

Text #10

Max Range: 0.3136. Min Range: -0.3136

Max Act: 0.2601. Min Act: -0.0000

Data Index: 89287 (C4 (Web Text))

Max Activating Token Index: 873

Text #11

Max Range: 0.3136. Min Range: -0.3136

Max Act: 0.2534. Min Act: -0.0000

Data Index: 326740 (C4 (Web Text))

Max Activating Token Index: 1000

Text #12

Max Range: 0.3136. Min Range: -0.3136

Max Act: 0.2641. Min Act: -0.0000

Data Index: 573456 (C4 (Web Text))

Max Activating Token Index: 848

Text #13

Max Range: 0.3136. Min Range: -0.3136

Max Act: 0.2438. Min Act: -0.0000

Data Index: 742709 (C4 (Web Text))

Max Activating Token Index: 833

Text #14

Max Range: 0.3136. Min Range: -0.3136

Max Act: 0.2455. Min Act: -0.0000

Data Index: 1317276 (C4 (Web Text))

Max Activating Token Index: 835

Text #15

Max Range: 0.3136. Min Range: -0.3136

Max Act: 0.2341. Min Act: -0.0000

Data Index: 257949 (C4 (Web Text))

Max Activating Token Index: 670

Text #16

Max Range: 0.3136. Min Range: -0.3136

Max Act: 0.2458. Min Act: -0.0000

Data Index: 144162 (C4 (Web Text))

Max Activating Token Index: 845

Text #17

Max Range: 0.3136. Min Range: -0.3136

Max Act: 0.2423. Min Act: -0.0000

Data Index: 97997 (C4 (Web Text))

Max Activating Token Index: 390

Text #18

Max Range: 0.3136. Min Range: -0.3136

Max Act: 0.2533. Min Act: -0.0000

Data Index: 972724 (C4 (Web Text))

Max Activating Token Index: 708

Text #19

Max Range: 0.3136. Min Range: -0.3136

Max Act: 0.2385. Min Act: -0.0000

Data Index: 807253 (C4 (Web Text))

Max Activating Token Index: 878