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

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

Neuron 3507 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2572. Min Range: -2.2572

Max Act: 2.2572. Min Act: -0.0000

Data Index: 1202852 (C4 (Web Text))

Max Activating Token Index: 526

Text #1

Max Range: 2.2572. Min Range: -2.2572

Max Act: 2.0481. Min Act: -0.0000

Data Index: 607049 (C4 (Web Text))

Max Activating Token Index: 792

Text #2

Max Range: 2.2572. Min Range: -2.2572

Max Act: 2.0394. Min Act: -0.0000

Data Index: 353676 (C4 (Web Text))

Max Activating Token Index: 159

Text #3

Max Range: 2.2572. Min Range: -2.2572

Max Act: 1.7719. Min Act: -0.0000

Data Index: 865334 (C4 (Web Text))

Max Activating Token Index: 169

Text #4

Max Range: 2.2572. Min Range: -2.2572

Max Act: 1.7711. Min Act: -0.0000

Data Index: 923462 (C4 (Web Text))

Max Activating Token Index: 291

Text #5

Max Range: 2.2572. Min Range: -2.2572

Max Act: 1.7819. Min Act: -0.0000

Data Index: 207358 (C4 (Web Text))

Max Activating Token Index: 644

Text #6

Max Range: 2.2572. Min Range: -2.2572

Max Act: 1.8162. Min Act: -0.0000

Data Index: 26562 (C4 (Web Text))

Max Activating Token Index: 553

Text #7

Max Range: 2.2572. Min Range: -2.2572

Max Act: 1.6212. Min Act: -0.0000

Data Index: 965359 (C4 (Web Text))

Max Activating Token Index: 800

Text #8

Max Range: 2.2572. Min Range: -2.2572

Max Act: 1.6564. Min Act: -0.0000

Data Index: 73201 (C4 (Web Text))

Max Activating Token Index: 240

Text #9

Max Range: 2.2572. Min Range: -2.2572

Max Act: 1.6084. Min Act: -0.0000

Data Index: 1359266 (C4 (Web Text))

Max Activating Token Index: 339

Text #10

Max Range: 2.2572. Min Range: -2.2572

Max Act: 1.5922. Min Act: -0.0000

Data Index: 1100232 (C4 (Web Text))

Max Activating Token Index: 530

Text #11

Max Range: 2.2572. Min Range: -2.2572

Max Act: 1.4778. Min Act: -0.0000

Data Index: 967981 (C4 (Web Text))

Max Activating Token Index: 550

Text #12

Max Range: 2.2572. Min Range: -2.2572

Max Act: 1.5631. Min Act: -0.0000

Data Index: 148125 (C4 (Web Text))

Max Activating Token Index: 130

Text #13

Max Range: 2.2572. Min Range: -2.2572

Max Act: 1.5436. Min Act: -0.0000

Data Index: 1176914 (C4 (Web Text))

Max Activating Token Index: 333

Text #14

Max Range: 2.2572. Min Range: -2.2572

Max Act: 1.5925. Min Act: -0.0000

Data Index: 1310313 (C4 (Web Text))

Max Activating Token Index: 309

Text #15

Max Range: 2.2572. Min Range: -2.2572

Max Act: 1.3121. Min Act: -0.0000

Data Index: 42237 (C4 (Web Text))

Max Activating Token Index: 268

Text #16

Max Range: 2.2572. Min Range: -2.2572

Max Act: 1.3424. Min Act: -0.0000

Data Index: 507564 (C4 (Web Text))

Max Activating Token Index: 676

Text #17

Max Range: 2.2572. Min Range: -2.2572

Max Act: 1.3323. Min Act: -0.0000

Data Index: 454864 (C4 (Web Text))

Max Activating Token Index: 234

Text #18

Max Range: 2.2572. Min Range: -2.2572

Max Act: 1.6326. Min Act: -0.0000

Data Index: 338846 (C4 (Web Text))

Max Activating Token Index: 886

Text #19

Max Range: 2.2572. Min Range: -2.2572

Max Act: 1.3082. Min Act: -0.0000

Data Index: 783932 (C4 (Web Text))

Max Activating Token Index: 527