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

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

Neuron 1813 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5585. Min Range: -0.5585

Max Act: 0.5585. Min Act: -0.0001

Data Index: 79864 (C4 (Web Text))

Max Activating Token Index: 420

Text #1

Max Range: 0.5585. Min Range: -0.5585

Max Act: 0.3074. Min Act: -0.0001

Data Index: 1012330 (C4 (Web Text))

Max Activating Token Index: 257

Text #2

Max Range: 0.5585. Min Range: -0.5585

Max Act: 0.3431. Min Act: -0.0001

Data Index: 151100 (C4 (Web Text))

Max Activating Token Index: 882

Text #3

Max Range: 0.5585. Min Range: -0.5585

Max Act: 0.3191. Min Act: -0.0001

Data Index: 787067 (C4 (Web Text))

Max Activating Token Index: 38

Text #4

Max Range: 0.5585. Min Range: -0.5585

Max Act: 0.3210. Min Act: -0.0001

Data Index: 802371 (C4 (Web Text))

Max Activating Token Index: 267

Text #5

Max Range: 0.5585. Min Range: -0.5585

Max Act: 0.3171. Min Act: -0.0001

Data Index: 480654 (C4 (Web Text))

Max Activating Token Index: 427

Text #6

Max Range: 0.5585. Min Range: -0.5585

Max Act: 0.3139. Min Act: -0.0001

Data Index: 1171439 (C4 (Web Text))

Max Activating Token Index: 412

Text #7

Max Range: 0.5585. Min Range: -0.5585

Max Act: 0.3023. Min Act: -0.0001

Data Index: 725733 (C4 (Web Text))

Max Activating Token Index: 655

Text #8

Max Range: 0.5585. Min Range: -0.5585

Max Act: 0.2732. Min Act: -0.0001

Data Index: 1299974 (C4 (Web Text))

Max Activating Token Index: 700

Text #9

Max Range: 0.5585. Min Range: -0.5585

Max Act: 0.2889. Min Act: -0.0001

Data Index: 1005625 (C4 (Web Text))

Max Activating Token Index: 930

Text #10

Max Range: 0.5585. Min Range: -0.5585

Max Act: 0.3008. Min Act: -0.0001

Data Index: 32999 (C4 (Web Text))

Max Activating Token Index: 820

Text #11

Max Range: 0.5585. Min Range: -0.5585

Max Act: 0.2967. Min Act: -0.0001

Data Index: 735212 (C4 (Web Text))

Max Activating Token Index: 744

Text #12

Max Range: 0.5585. Min Range: -0.5585

Max Act: 0.3151. Min Act: -0.0001

Data Index: 667253 (C4 (Web Text))

Max Activating Token Index: 626

Text #13

Max Range: 0.5585. Min Range: -0.5585

Max Act: 0.3042. Min Act: -0.0001

Data Index: 914348 (C4 (Web Text))

Max Activating Token Index: 575

Text #14

Max Range: 0.5585. Min Range: -0.5585

Max Act: 0.2934. Min Act: -0.0001

Data Index: 1011318 (C4 (Web Text))

Max Activating Token Index: 55

Text #15

Max Range: 0.5585. Min Range: -0.5585

Max Act: 0.2692. Min Act: -0.0001

Data Index: 527498 (C4 (Web Text))

Max Activating Token Index: 673

Text #16

Max Range: 0.5585. Min Range: -0.5585

Max Act: 0.2866. Min Act: -0.0001

Data Index: 746521 (C4 (Web Text))

Max Activating Token Index: 491

Text #17

Max Range: 0.5585. Min Range: -0.5585

Max Act: 0.2700. Min Act: -0.0001

Data Index: 117552 (C4 (Web Text))

Max Activating Token Index: 819

Text #18

Max Range: 0.5585. Min Range: -0.5585

Max Act: 0.2858. Min Act: -0.0001

Data Index: 33382 (C4 (Web Text))

Max Activating Token Index: 14

Text #19

Max Range: 0.5585. Min Range: -0.5585

Max Act: 0.2755. Min Act: -0.0001

Data Index: 637161 (C4 (Web Text))

Max Activating Token Index: 721