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

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

Neuron 1254 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4511. Min Range: -0.4511

Max Act: 0.4216. Min Act: -0.0000

Data Index: 277283 (C4 (Web Text))

Max Activating Token Index: 750

Text #1

Max Range: 0.4511. Min Range: -0.4511

Max Act: 0.4511. Min Act: -0.0000

Data Index: 983367 (C4 (Web Text))

Max Activating Token Index: 220

Text #2

Max Range: 0.4511. Min Range: -0.4511

Max Act: 0.3724. Min Act: -0.0000

Data Index: 953396 (C4 (Web Text))

Max Activating Token Index: 210

Text #3

Max Range: 0.4511. Min Range: -0.4511

Max Act: 0.3262. Min Act: -0.0000

Data Index: 825193 (C4 (Web Text))

Max Activating Token Index: 643

Text #4

Max Range: 0.4511. Min Range: -0.4511

Max Act: 0.3087. Min Act: -0.0000

Data Index: 1031142 (C4 (Web Text))

Max Activating Token Index: 460

Text #5

Max Range: 0.4511. Min Range: -0.4511

Max Act: 0.2982. Min Act: -0.0000

Data Index: 55709 (C4 (Web Text))

Max Activating Token Index: 70

Text #6

Max Range: 0.4511. Min Range: -0.4511

Max Act: 0.2882. Min Act: -0.0000

Data Index: 1248779 (C4 (Web Text))

Max Activating Token Index: 433

Text #7

Max Range: 0.4511. Min Range: -0.4511

Max Act: 0.2933. Min Act: -0.0000

Data Index: 769244 (C4 (Web Text))

Max Activating Token Index: 311

Text #8

Max Range: 0.4511. Min Range: -0.4511

Max Act: 0.2726. Min Act: -0.0000

Data Index: 897231 (C4 (Web Text))

Max Activating Token Index: 122

Text #9

Max Range: 0.4511. Min Range: -0.4511

Max Act: 0.2868. Min Act: -0.0000

Data Index: 1055273 (C4 (Web Text))

Max Activating Token Index: 892

Text #10

Max Range: 0.4511. Min Range: -0.4511

Max Act: 0.2536. Min Act: -0.0000

Data Index: 294024 (C4 (Web Text))

Max Activating Token Index: 929

Text #11

Max Range: 0.4511. Min Range: -0.4511

Max Act: 0.2732. Min Act: -0.0000

Data Index: 509869 (C4 (Web Text))

Max Activating Token Index: 535

Text #12

Max Range: 0.4511. Min Range: -0.4511

Max Act: 0.2722. Min Act: -0.0000

Data Index: 1277960 (C4 (Web Text))

Max Activating Token Index: 496

Text #13

Max Range: 0.4511. Min Range: -0.4511

Max Act: 0.2648. Min Act: -0.0000

Data Index: 58897 (C4 (Web Text))

Max Activating Token Index: 161

Text #14

Max Range: 0.4511. Min Range: -0.4511

Max Act: 0.2659. Min Act: -0.0000

Data Index: 1258405 (C4 (Web Text))

Max Activating Token Index: 8

Text #15

Max Range: 0.4511. Min Range: -0.4511

Max Act: 0.2404. Min Act: -0.0000

Data Index: 597205 (C4 (Web Text))

Max Activating Token Index: 877

Text #16

Max Range: 0.4511. Min Range: -0.4511

Max Act: 0.2423. Min Act: -0.0000

Data Index: 949311 (C4 (Web Text))

Max Activating Token Index: 781

Text #17

Max Range: 0.4511. Min Range: -0.4511

Max Act: 0.2460. Min Act: -0.0000

Data Index: 1024329 (C4 (Web Text))

Max Activating Token Index: 94

Text #18

Max Range: 0.4511. Min Range: -0.4511

Max Act: 0.2556. Min Act: -0.0000

Data Index: 835451 (C4 (Web Text))

Max Activating Token Index: 260

Text #19

Max Range: 0.4511. Min Range: -0.4511

Max Act: 0.2704. Min Act: 0.0000

Data Index: 1006447 (C4 (Web Text))

Max Activating Token Index: 9