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

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

Neuron 1525 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.3460. Min Range: -0.3460

Max Act: 0.3370. Min Act: -0.0003

Data Index: 170690 (C4 (Web Text))

Max Activating Token Index: 719

Text #1

Max Range: 0.3460. Min Range: -0.3460

Max Act: 0.3460. Min Act: -0.0003

Data Index: 613599 (C4 (Web Text))

Max Activating Token Index: 837

Text #2

Max Range: 0.3460. Min Range: -0.3460

Max Act: 0.3170. Min Act: -0.0003

Data Index: 1221015 (C4 (Web Text))

Max Activating Token Index: 600

Text #3

Max Range: 0.3460. Min Range: -0.3460

Max Act: 0.2996. Min Act: -0.0003

Data Index: 1343764 (C4 (Web Text))

Max Activating Token Index: 533

Text #4

Max Range: 0.3460. Min Range: -0.3460

Max Act: 0.2995. Min Act: -0.0003

Data Index: 947314 (C4 (Web Text))

Max Activating Token Index: 661

Text #5

Max Range: 0.3460. Min Range: -0.3460

Max Act: 0.2879. Min Act: -0.0003

Data Index: 70389 (C4 (Web Text))

Max Activating Token Index: 701

Text #6

Max Range: 0.3460. Min Range: -0.3460

Max Act: 0.2909. Min Act: -0.0003

Data Index: 325673 (C4 (Web Text))

Max Activating Token Index: 740

Text #7

Max Range: 0.3460. Min Range: -0.3460

Max Act: 0.2904. Min Act: -0.0003

Data Index: 283009 (C4 (Web Text))

Max Activating Token Index: 668

Text #8

Max Range: 0.3460. Min Range: -0.3460

Max Act: 0.2796. Min Act: -0.0003

Data Index: 174439 (C4 (Web Text))

Max Activating Token Index: 561

Text #9

Max Range: 0.3460. Min Range: -0.3460

Max Act: 0.2955. Min Act: -0.0003

Data Index: 716293 (C4 (Web Text))

Max Activating Token Index: 453

Text #10

Max Range: 0.3460. Min Range: -0.3460

Max Act: 0.2956. Min Act: -0.0003

Data Index: 65240 (C4 (Web Text))

Max Activating Token Index: 332

Text #11

Max Range: 0.3460. Min Range: -0.3460

Max Act: 0.2710. Min Act: -0.0003

Data Index: 1295302 (C4 (Web Text))

Max Activating Token Index: 827

Text #12

Max Range: 0.3460. Min Range: -0.3460

Max Act: 0.2761. Min Act: -0.0003

Data Index: 717022 (C4 (Web Text))

Max Activating Token Index: 392

Text #13

Max Range: 0.3460. Min Range: -0.3460

Max Act: 0.2847. Min Act: -0.0003

Data Index: 898672 (C4 (Web Text))

Max Activating Token Index: 983

Text #14

Max Range: 0.3460. Min Range: -0.3460

Max Act: 0.2746. Min Act: -0.0003

Data Index: 186809 (C4 (Web Text))

Max Activating Token Index: 578

Text #15

Max Range: 0.3460. Min Range: -0.3460

Max Act: 0.2740. Min Act: -0.0003

Data Index: 1056650 (C4 (Web Text))

Max Activating Token Index: 575

Text #16

Max Range: 0.3460. Min Range: -0.3460

Max Act: 0.2741. Min Act: -0.0003

Data Index: 1234981 (C4 (Web Text))

Max Activating Token Index: 692

Text #17

Max Range: 0.3460. Min Range: -0.3460

Max Act: 0.2723. Min Act: -0.0003

Data Index: 65343 (C4 (Web Text))

Max Activating Token Index: 500

Text #18

Max Range: 0.3460. Min Range: -0.3460

Max Act: 0.2720. Min Act: -0.0003

Data Index: 1272981 (C4 (Web Text))

Max Activating Token Index: 744

Text #19

Max Range: 0.3460. Min Range: -0.3460

Max Act: 0.2699. Min Act: -0.0003

Data Index: 524578 (C4 (Web Text))

Max Activating Token Index: 709