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

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

Neuron 2939 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3726. Min Range: -3.3726

Max Act: 3.3726. Min Act: -0.0000

Data Index: 768548 (C4 (Web Text))

Max Activating Token Index: 702

Text #1

Max Range: 3.3726. Min Range: -3.3726

Max Act: 2.6920. Min Act: -0.0000

Data Index: 1058124 (C4 (Web Text))

Max Activating Token Index: 946

Text #2

Max Range: 3.3726. Min Range: -3.3726

Max Act: 2.8149. Min Act: -0.0000

Data Index: 327965 (C4 (Web Text))

Max Activating Token Index: 339

Text #3

Max Range: 3.3726. Min Range: -3.3726

Max Act: 2.5879. Min Act: -0.0000

Data Index: 65490 (C4 (Web Text))

Max Activating Token Index: 582

Text #4

Max Range: 3.3726. Min Range: -3.3726

Max Act: 2.5750. Min Act: -0.0000

Data Index: 104591 (C4 (Web Text))

Max Activating Token Index: 4

Text #5

Max Range: 3.3726. Min Range: -3.3726

Max Act: 2.5711. Min Act: -0.0000

Data Index: 1299042 (C4 (Web Text))

Max Activating Token Index: 474

Text #6

Max Range: 3.3726. Min Range: -3.3726

Max Act: 2.4860. Min Act: -0.0000

Data Index: 291832 (C4 (Web Text))

Max Activating Token Index: 16

Text #7

Max Range: 3.3726. Min Range: -3.3726

Max Act: 2.4739. Min Act: -0.0000

Data Index: 645487 (C4 (Web Text))

Max Activating Token Index: 562

Text #8

Max Range: 3.3726. Min Range: -3.3726

Max Act: 2.5595. Min Act: -0.0000

Data Index: 113674 (C4 (Web Text))

Max Activating Token Index: 5

Text #9

Max Range: 3.3726. Min Range: -3.3726

Max Act: 2.4163. Min Act: -0.0000

Data Index: 49049 (C4 (Web Text))

Max Activating Token Index: 8

Text #10

Max Range: 3.3726. Min Range: -3.3726

Max Act: 2.5288. Min Act: -0.0000

Data Index: 405542 (C4 (Web Text))

Max Activating Token Index: 274

Text #11

Max Range: 3.3726. Min Range: -3.3726

Max Act: 2.2416. Min Act: -0.0000

Data Index: 514402 (C4 (Web Text))

Max Activating Token Index: 971

Text #12

Max Range: 3.3726. Min Range: -3.3726

Max Act: 2.3162. Min Act: -0.0000

Data Index: 829112 (C4 (Web Text))

Max Activating Token Index: 424

Text #13

Max Range: 3.3726. Min Range: -3.3726

Max Act: 2.2519. Min Act: -0.0000

Data Index: 730717 (C4 (Web Text))

Max Activating Token Index: 478

Text #14

Max Range: 3.3726. Min Range: -3.3726

Max Act: 2.2336. Min Act: -0.0000

Data Index: 747353 (C4 (Web Text))

Max Activating Token Index: 259

Text #15

Max Range: 3.3726. Min Range: -3.3726

Max Act: 2.1793. Min Act: -0.0000

Data Index: 90510 (C4 (Web Text))

Max Activating Token Index: 92

Text #16

Max Range: 3.3726. Min Range: -3.3726

Max Act: 2.1948. Min Act: -0.0000

Data Index: 1409665 (Python Code)

Max Activating Token Index: 225

Text #17

Max Range: 3.3726. Min Range: -3.3726

Max Act: 2.1572. Min Act: -0.0000

Data Index: 1325966 (C4 (Web Text))

Max Activating Token Index: 365

Text #18

Max Range: 3.3726. Min Range: -3.3726

Max Act: 2.1678. Min Act: -0.0000

Data Index: 941031 (C4 (Web Text))

Max Activating Token Index: 34

Text #19

Max Range: 3.3726. Min Range: -3.3726

Max Act: 2.1390. Min Act: -0.0000

Data Index: 65440 (C4 (Web Text))

Max Activating Token Index: 147