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

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

Neuron 5795 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.9212. Min Range: -6.9212

Max Act: 6.9212. Min Act: -0.0000

Data Index: 855190 (C4 (Web Text))

Max Activating Token Index: 840

Text #1

Max Range: 6.9212. Min Range: -6.9212

Max Act: 6.9149. Min Act: -0.0000

Data Index: 1355767 (C4 (Web Text))

Max Activating Token Index: 104

Text #2

Max Range: 6.9212. Min Range: -6.9212

Max Act: 6.7796. Min Act: -0.0000

Data Index: 988563 (C4 (Web Text))

Max Activating Token Index: 368

Text #3

Max Range: 6.9212. Min Range: -6.9212

Max Act: 6.5877. Min Act: -0.0000

Data Index: 987283 (C4 (Web Text))

Max Activating Token Index: 14

Text #4

Max Range: 6.9212. Min Range: -6.9212

Max Act: 6.6278. Min Act: -0.0000

Data Index: 795763 (C4 (Web Text))

Max Activating Token Index: 360

Text #5

Max Range: 6.9212. Min Range: -6.9212

Max Act: 6.3492. Min Act: -0.0000

Data Index: 1080112 (C4 (Web Text))

Max Activating Token Index: 348

Text #6

Max Range: 6.9212. Min Range: -6.9212

Max Act: 6.3646. Min Act: -0.0000

Data Index: 44104 (C4 (Web Text))

Max Activating Token Index: 64

Text #7

Max Range: 6.9212. Min Range: -6.9212

Max Act: 6.2473. Min Act: -0.0000

Data Index: 84245 (C4 (Web Text))

Max Activating Token Index: 314

Text #8

Max Range: 6.9212. Min Range: -6.9212

Max Act: 6.1894. Min Act: -0.0000

Data Index: 1327172 (C4 (Web Text))

Max Activating Token Index: 711

Text #9

Max Range: 6.9212. Min Range: -6.9212

Max Act: 6.1301. Min Act: -0.0000

Data Index: 665309 (C4 (Web Text))

Max Activating Token Index: 530

Text #10

Max Range: 6.9212. Min Range: -6.9212

Max Act: 6.0346. Min Act: -0.0000

Data Index: 150685 (C4 (Web Text))

Max Activating Token Index: 15

Text #11

Max Range: 6.9212. Min Range: -6.9212

Max Act: 5.9812. Min Act: -0.0000

Data Index: 619537 (C4 (Web Text))

Max Activating Token Index: 836

Text #12

Max Range: 6.9212. Min Range: -6.9212

Max Act: 5.9585. Min Act: -0.0000

Data Index: 597034 (C4 (Web Text))

Max Activating Token Index: 506

Text #13

Max Range: 6.9212. Min Range: -6.9212

Max Act: 5.8962. Min Act: -0.0000

Data Index: 257195 (C4 (Web Text))

Max Activating Token Index: 155

Text #14

Max Range: 6.9212. Min Range: -6.9212

Max Act: 5.6726. Min Act: -0.0000

Data Index: 530287 (C4 (Web Text))

Max Activating Token Index: 691

Text #15

Max Range: 6.9212. Min Range: -6.9212

Max Act: 5.7469. Min Act: -0.0000

Data Index: 1169690 (C4 (Web Text))

Max Activating Token Index: 583

Text #16

Max Range: 6.9212. Min Range: -6.9212

Max Act: 5.7038. Min Act: -0.0000

Data Index: 1130352 (C4 (Web Text))

Max Activating Token Index: 15

Text #17

Max Range: 6.9212. Min Range: -6.9212

Max Act: 5.6838. Min Act: -0.0000

Data Index: 550736 (C4 (Web Text))

Max Activating Token Index: 291

Text #18

Max Range: 6.9212. Min Range: -6.9212

Max Act: 5.6670. Min Act: -0.0000

Data Index: 1348818 (C4 (Web Text))

Max Activating Token Index: 390

Text #19

Max Range: 6.9212. Min Range: -6.9212

Max Act: 5.4610. Min Act: -0.0000

Data Index: 680545 (C4 (Web Text))

Max Activating Token Index: 153