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

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

Neuron 5755 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: 0.3591. Min Range: -0.3591

Max Act: 0.3591. Min Act: -0.0000

Data Index: 736202 (C4 (Web Text))

Max Activating Token Index: 485

Text #1

Max Range: 0.3591. Min Range: -0.3591

Max Act: 0.3587. Min Act: -0.0000

Data Index: 421747 (C4 (Web Text))

Max Activating Token Index: 700

Text #2

Max Range: 0.3591. Min Range: -0.3591

Max Act: 0.3103. Min Act: -0.0000

Data Index: 297 (C4 (Web Text))

Max Activating Token Index: 851

Text #3

Max Range: 0.3591. Min Range: -0.3591

Max Act: 0.3342. Min Act: -0.0000

Data Index: 75220 (C4 (Web Text))

Max Activating Token Index: 470

Text #4

Max Range: 0.3591. Min Range: -0.3591

Max Act: 0.3018. Min Act: -0.0000

Data Index: 1148985 (C4 (Web Text))

Max Activating Token Index: 309

Text #5

Max Range: 0.3591. Min Range: -0.3591

Max Act: 0.2992. Min Act: -0.0000

Data Index: 152021 (C4 (Web Text))

Max Activating Token Index: 286

Text #6

Max Range: 0.3591. Min Range: -0.3591

Max Act: 0.3006. Min Act: -0.0000

Data Index: 351608 (C4 (Web Text))

Max Activating Token Index: 46

Text #7

Max Range: 0.3591. Min Range: -0.3591

Max Act: 0.2899. Min Act: -0.0000

Data Index: 12598 (C4 (Web Text))

Max Activating Token Index: 423

Text #8

Max Range: 0.3591. Min Range: -0.3591

Max Act: 0.2731. Min Act: -0.0000

Data Index: 612134 (C4 (Web Text))

Max Activating Token Index: 447

Text #9

Max Range: 0.3591. Min Range: -0.3591

Max Act: 0.3023. Min Act: -0.0000

Data Index: 343254 (C4 (Web Text))

Max Activating Token Index: 65

Text #10

Max Range: 0.3591. Min Range: -0.3591

Max Act: 0.2810. Min Act: -0.0000

Data Index: 786484 (C4 (Web Text))

Max Activating Token Index: 244

Text #11

Max Range: 0.3591. Min Range: -0.3591

Max Act: 0.3052. Min Act: -0.0000

Data Index: 765499 (C4 (Web Text))

Max Activating Token Index: 287

Text #12

Max Range: 0.3591. Min Range: -0.3591

Max Act: 0.2771. Min Act: -0.0000

Data Index: 101924 (C4 (Web Text))

Max Activating Token Index: 513

Text #13

Max Range: 0.3591. Min Range: -0.3591

Max Act: 0.2831. Min Act: -0.0000

Data Index: 481896 (C4 (Web Text))

Max Activating Token Index: 44

Text #14

Max Range: 0.3591. Min Range: -0.3591

Max Act: 0.2813. Min Act: -0.0000

Data Index: 1335344 (C4 (Web Text))

Max Activating Token Index: 498

Text #15

Max Range: 0.3591. Min Range: -0.3591

Max Act: 0.2894. Min Act: -0.0000

Data Index: 908449 (C4 (Web Text))

Max Activating Token Index: 69

Text #16

Max Range: 0.3591. Min Range: -0.3591

Max Act: 0.2874. Min Act: -0.0000

Data Index: 691007 (C4 (Web Text))

Max Activating Token Index: 663

Text #17

Max Range: 0.3591. Min Range: -0.3591

Max Act: 0.3165. Min Act: -0.0000

Data Index: 270931 (C4 (Web Text))

Max Activating Token Index: 389

Text #18

Max Range: 0.3591. Min Range: -0.3591

Max Act: 0.2549. Min Act: -0.0000

Data Index: 493571 (C4 (Web Text))

Max Activating Token Index: 308

Text #19

Max Range: 0.3591. Min Range: -0.3591

Max Act: 0.2588. Min Act: -0.0000

Data Index: 294425 (C4 (Web Text))

Max Activating Token Index: 423