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

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

Neuron 2908 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4028. Min Range: -0.4028

Max Act: 0.4028. Min Act: -0.0000

Data Index: 1246790 (C4 (Web Text))

Max Activating Token Index: 57

Text #1

Max Range: 0.4028. Min Range: -0.4028

Max Act: 0.3409. Min Act: -0.0000

Data Index: 1336882 (C4 (Web Text))

Max Activating Token Index: 237

Text #2

Max Range: 0.4028. Min Range: -0.4028

Max Act: 0.3152. Min Act: -0.0000

Data Index: 813543 (C4 (Web Text))

Max Activating Token Index: 437

Text #3

Max Range: 0.4028. Min Range: -0.4028

Max Act: 0.3023. Min Act: -0.0000

Data Index: 700662 (C4 (Web Text))

Max Activating Token Index: 343

Text #4

Max Range: 0.4028. Min Range: -0.4028

Max Act: 0.3108. Min Act: -0.0000

Data Index: 145126 (C4 (Web Text))

Max Activating Token Index: 705

Text #5

Max Range: 0.4028. Min Range: -0.4028

Max Act: 0.3085. Min Act: -0.0000

Data Index: 920868 (C4 (Web Text))

Max Activating Token Index: 648

Text #6

Max Range: 0.4028. Min Range: -0.4028

Max Act: 0.3011. Min Act: -0.0000

Data Index: 1046822 (C4 (Web Text))

Max Activating Token Index: 713

Text #7

Max Range: 0.4028. Min Range: -0.4028

Max Act: 0.3018. Min Act: -0.0000

Data Index: 757657 (C4 (Web Text))

Max Activating Token Index: 142

Text #8

Max Range: 0.4028. Min Range: -0.4028

Max Act: 0.3069. Min Act: -0.0000

Data Index: 1403742 (Python Code)

Max Activating Token Index: 667

Text #9

Max Range: 0.4028. Min Range: -0.4028

Max Act: 0.2953. Min Act: -0.0000

Data Index: 1540832 (Python Code)

Max Activating Token Index: 28

Text #10

Max Range: 0.4028. Min Range: -0.4028

Max Act: 0.2791. Min Act: -0.0000

Data Index: 1474957 (Python Code)

Max Activating Token Index: 108

Text #11

Max Range: 0.4028. Min Range: -0.4028

Max Act: 0.2878. Min Act: -0.0000

Data Index: 1093290 (C4 (Web Text))

Max Activating Token Index: 302

Text #12

Max Range: 0.4028. Min Range: -0.4028

Max Act: 0.2665. Min Act: 0.0000

Data Index: 1254732 (C4 (Web Text))

Max Activating Token Index: 333

Text #13

Max Range: 0.4028. Min Range: -0.4028

Max Act: 0.2831. Min Act: -0.0000

Data Index: 485200 (C4 (Web Text))

Max Activating Token Index: 396

Text #14

Max Range: 0.4028. Min Range: -0.4028

Max Act: 0.2726. Min Act: -0.0000

Data Index: 51940 (C4 (Web Text))

Max Activating Token Index: 113

Text #15

Max Range: 0.4028. Min Range: -0.4028

Max Act: 0.2724. Min Act: -0.0000

Data Index: 968722 (C4 (Web Text))

Max Activating Token Index: 807

Text #16

Max Range: 0.4028. Min Range: -0.4028

Max Act: 0.2806. Min Act: -0.0000

Data Index: 1614117 (Python Code)

Max Activating Token Index: 330

Text #17

Max Range: 0.4028. Min Range: -0.4028

Max Act: 0.2645. Min Act: -0.0000

Data Index: 102984 (C4 (Web Text))

Max Activating Token Index: 114

Text #18

Max Range: 0.4028. Min Range: -0.4028

Max Act: 0.2814. Min Act: -0.0000

Data Index: 851930 (C4 (Web Text))

Max Activating Token Index: 290

Text #19

Max Range: 0.4028. Min Range: -0.4028

Max Act: 0.2684. Min Act: -0.0000

Data Index: 1100520 (C4 (Web Text))

Max Activating Token Index: 186