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

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

Neuron 2938 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.4090. Min Range: -5.4090

Max Act: 5.4090. Min Act: -0.0000

Data Index: 662287 (C4 (Web Text))

Max Activating Token Index: 237

Text #1

Max Range: 5.4090. Min Range: -5.4090

Max Act: 5.3764. Min Act: -0.0000

Data Index: 1132905 (C4 (Web Text))

Max Activating Token Index: 665

Text #2

Max Range: 5.4090. Min Range: -5.4090

Max Act: 4.7052. Min Act: -0.0000

Data Index: 543736 (C4 (Web Text))

Max Activating Token Index: 378

Text #3

Max Range: 5.4090. Min Range: -5.4090

Max Act: 4.1019. Min Act: -0.0000

Data Index: 547163 (C4 (Web Text))

Max Activating Token Index: 798

Text #4

Max Range: 5.4090. Min Range: -5.4090

Max Act: 4.3656. Min Act: -0.0000

Data Index: 1220646 (C4 (Web Text))

Max Activating Token Index: 933

Text #5

Max Range: 5.4090. Min Range: -5.4090

Max Act: 4.1258. Min Act: -0.0000

Data Index: 1042216 (C4 (Web Text))

Max Activating Token Index: 302

Text #6

Max Range: 5.4090. Min Range: -5.4090

Max Act: 4.1240. Min Act: -0.0000

Data Index: 1014516 (C4 (Web Text))

Max Activating Token Index: 700

Text #7

Max Range: 5.4090. Min Range: -5.4090

Max Act: 4.3994. Min Act: -0.0000

Data Index: 282043 (C4 (Web Text))

Max Activating Token Index: 656

Text #8

Max Range: 5.4090. Min Range: -5.4090

Max Act: 4.2301. Min Act: -0.0000

Data Index: 940607 (C4 (Web Text))

Max Activating Token Index: 959

Text #9

Max Range: 5.4090. Min Range: -5.4090

Max Act: 4.2513. Min Act: -0.0000

Data Index: 1238636 (C4 (Web Text))

Max Activating Token Index: 585

Text #10

Max Range: 5.4090. Min Range: -5.4090

Max Act: 4.0907. Min Act: -0.0000

Data Index: 418539 (C4 (Web Text))

Max Activating Token Index: 961

Text #11

Max Range: 5.4090. Min Range: -5.4090

Max Act: 4.0773. Min Act: -0.0000

Data Index: 1095797 (C4 (Web Text))

Max Activating Token Index: 243

Text #12

Max Range: 5.4090. Min Range: -5.4090

Max Act: 4.0700. Min Act: -0.0000

Data Index: 878969 (C4 (Web Text))

Max Activating Token Index: 156

Text #13

Max Range: 5.4090. Min Range: -5.4090

Max Act: 3.9422. Min Act: -0.0000

Data Index: 697785 (C4 (Web Text))

Max Activating Token Index: 959

Text #14

Max Range: 5.4090. Min Range: -5.4090

Max Act: 3.9935. Min Act: 0.0001

Data Index: 649589 (C4 (Web Text))

Max Activating Token Index: 31

Text #15

Max Range: 5.4090. Min Range: -5.4090

Max Act: 3.6342. Min Act: -0.0000

Data Index: 458052 (C4 (Web Text))

Max Activating Token Index: 293

Text #16

Max Range: 5.4090. Min Range: -5.4090

Max Act: 3.9184. Min Act: -0.0000

Data Index: 577621 (C4 (Web Text))

Max Activating Token Index: 893

Text #17

Max Range: 5.4090. Min Range: -5.4090

Max Act: 3.8977. Min Act: -0.0000

Data Index: 207005 (C4 (Web Text))

Max Activating Token Index: 447

Text #18

Max Range: 5.4090. Min Range: -5.4090

Max Act: 3.7391. Min Act: -0.0000

Data Index: 604432 (C4 (Web Text))

Max Activating Token Index: 794

Text #19

Max Range: 5.4090. Min Range: -5.4090

Max Act: 3.8575. Min Act: -0.0000

Data Index: 862533 (C4 (Web Text))

Max Activating Token Index: 188