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

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

Neuron 2681 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.1554. Min Range: -6.1554

Max Act: 5.9756. Min Act: -0.0001

Data Index: 1330461 (C4 (Web Text))

Max Activating Token Index: 105

Text #1

Max Range: 6.1554. Min Range: -6.1554

Max Act: 6.1554. Min Act: -0.0001

Data Index: 1033507 (C4 (Web Text))

Max Activating Token Index: 362

Text #2

Max Range: 6.1554. Min Range: -6.1554

Max Act: 5.9537. Min Act: -0.0001

Data Index: 534650 (C4 (Web Text))

Max Activating Token Index: 28

Text #3

Max Range: 6.1554. Min Range: -6.1554

Max Act: 6.1327. Min Act: -0.0001

Data Index: 389088 (C4 (Web Text))

Max Activating Token Index: 57

Text #4

Max Range: 6.1554. Min Range: -6.1554

Max Act: 5.6459. Min Act: -0.0001

Data Index: 183977 (C4 (Web Text))

Max Activating Token Index: 147

Text #5

Max Range: 6.1554. Min Range: -6.1554

Max Act: 5.3351. Min Act: -0.0001

Data Index: 1179864 (C4 (Web Text))

Max Activating Token Index: 332

Text #6

Max Range: 6.1554. Min Range: -6.1554

Max Act: 5.1639. Min Act: -0.0001

Data Index: 1151256 (C4 (Web Text))

Max Activating Token Index: 779

Text #7

Max Range: 6.1554. Min Range: -6.1554

Max Act: 5.5000. Min Act: -0.0001

Data Index: 931696 (C4 (Web Text))

Max Activating Token Index: 183

Text #8

Max Range: 6.1554. Min Range: -6.1554

Max Act: 5.8005. Min Act: -0.0001

Data Index: 550828 (C4 (Web Text))

Max Activating Token Index: 396

Text #9

Max Range: 6.1554. Min Range: -6.1554

Max Act: 5.6417. Min Act: -0.0001

Data Index: 1006933 (C4 (Web Text))

Max Activating Token Index: 675

Text #10

Max Range: 6.1554. Min Range: -6.1554

Max Act: 5.5845. Min Act: -0.0001

Data Index: 599764 (C4 (Web Text))

Max Activating Token Index: 203

Text #11

Max Range: 6.1554. Min Range: -6.1554

Max Act: 5.1846. Min Act: -0.0001

Data Index: 299631 (C4 (Web Text))

Max Activating Token Index: 36

Text #12

Max Range: 6.1554. Min Range: -6.1554

Max Act: 5.4967. Min Act: -0.0001

Data Index: 1265186 (C4 (Web Text))

Max Activating Token Index: 355

Text #13

Max Range: 6.1554. Min Range: -6.1554

Max Act: 5.3442. Min Act: -0.0001

Data Index: 289332 (C4 (Web Text))

Max Activating Token Index: 534

Text #14

Max Range: 6.1554. Min Range: -6.1554

Max Act: 5.3187. Min Act: -0.0001

Data Index: 424214 (C4 (Web Text))

Max Activating Token Index: 632

Text #15

Max Range: 6.1554. Min Range: -6.1554

Max Act: 5.4462. Min Act: -0.0001

Data Index: 1116792 (C4 (Web Text))

Max Activating Token Index: 656

Text #16

Max Range: 6.1554. Min Range: -6.1554

Max Act: 5.1858. Min Act: -0.0001

Data Index: 347661 (C4 (Web Text))

Max Activating Token Index: 15

Text #17

Max Range: 6.1554. Min Range: -6.1554

Max Act: 5.3379. Min Act: -0.0001

Data Index: 359656 (C4 (Web Text))

Max Activating Token Index: 88

Text #18

Max Range: 6.1554. Min Range: -6.1554

Max Act: 5.1430. Min Act: -0.0001

Data Index: 621447 (C4 (Web Text))

Max Activating Token Index: 750

Text #19

Max Range: 6.1554. Min Range: -6.1554

Max Act: 5.2631. Min Act: -0.0001

Data Index: 1029449 (C4 (Web Text))

Max Activating Token Index: 877