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

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

Neuron 366 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: 0.3784. Min Range: -0.3784

Max Act: 0.3784. Min Act: -0.0001

Data Index: 1222705 (C4 (Web Text))

Max Activating Token Index: 745

Text #1

Max Range: 0.3784. Min Range: -0.3784

Max Act: 0.3608. Min Act: 0.0000

Data Index: 517730 (C4 (Web Text))

Max Activating Token Index: 598

Text #2

Max Range: 0.3784. Min Range: -0.3784

Max Act: 0.3253. Min Act: -0.0000

Data Index: 1281461 (C4 (Web Text))

Max Activating Token Index: 804

Text #3

Max Range: 0.3784. Min Range: -0.3784

Max Act: 0.3339. Min Act: -0.0000

Data Index: 1019256 (C4 (Web Text))

Max Activating Token Index: 35

Text #4

Max Range: 0.3784. Min Range: -0.3784

Max Act: 0.3326. Min Act: -0.0001

Data Index: 1007662 (C4 (Web Text))

Max Activating Token Index: 541

Text #5

Max Range: 0.3784. Min Range: -0.3784

Max Act: 0.3125. Min Act: 0.0001

Data Index: 634656 (C4 (Web Text))

Max Activating Token Index: 1017

Text #6

Max Range: 0.3784. Min Range: -0.3784

Max Act: 0.3136. Min Act: -0.0000

Data Index: 722707 (C4 (Web Text))

Max Activating Token Index: 579

Text #7

Max Range: 0.3784. Min Range: -0.3784

Max Act: 0.3029. Min Act: -0.0000

Data Index: 789714 (C4 (Web Text))

Max Activating Token Index: 646

Text #8

Max Range: 0.3784. Min Range: -0.3784

Max Act: 0.3019. Min Act: -0.0000

Data Index: 124206 (C4 (Web Text))

Max Activating Token Index: 440

Text #9

Max Range: 0.3784. Min Range: -0.3784

Max Act: 0.3011. Min Act: -0.0000

Data Index: 532821 (C4 (Web Text))

Max Activating Token Index: 532

Text #10

Max Range: 0.3784. Min Range: -0.3784

Max Act: 0.2845. Min Act: -0.0001

Data Index: 946540 (C4 (Web Text))

Max Activating Token Index: 225

Text #11

Max Range: 0.3784. Min Range: -0.3784

Max Act: 0.3042. Min Act: 0.0001

Data Index: 230993 (C4 (Web Text))

Max Activating Token Index: 416

Text #12

Max Range: 0.3784. Min Range: -0.3784

Max Act: 0.2973. Min Act: -0.0001

Data Index: 798551 (C4 (Web Text))

Max Activating Token Index: 950

Text #13

Max Range: 0.3784. Min Range: -0.3784

Max Act: 0.2788. Min Act: -0.0000

Data Index: 912567 (C4 (Web Text))

Max Activating Token Index: 54

Text #14

Max Range: 0.3784. Min Range: -0.3784

Max Act: 0.2873. Min Act: -0.0000

Data Index: 778844 (C4 (Web Text))

Max Activating Token Index: 198

Text #15

Max Range: 0.3784. Min Range: -0.3784

Max Act: 0.2827. Min Act: 0.0001

Data Index: 1339887 (C4 (Web Text))

Max Activating Token Index: 584

Text #16

Max Range: 0.3784. Min Range: -0.3784

Max Act: 0.2851. Min Act: -0.0001

Data Index: 14094 (C4 (Web Text))

Max Activating Token Index: 728

Text #17

Max Range: 0.3784. Min Range: -0.3784

Max Act: 0.2888. Min Act: -0.0000

Data Index: 1126519 (C4 (Web Text))

Max Activating Token Index: 680

Text #18

Max Range: 0.3784. Min Range: -0.3784

Max Act: 0.2828. Min Act: 0.0001

Data Index: 1077990 (C4 (Web Text))

Max Activating Token Index: 463

Text #19

Max Range: 0.3784. Min Range: -0.3784

Max Act: 0.2819. Min Act: -0.0000

Data Index: 1028073 (C4 (Web Text))

Max Activating Token Index: 335