Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1203 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 3.0444. Min Range: -3.0444

Max Act: 3.0444. Min Act: -0.0000

Data Index: 865957 (C4 (Web Text))

Max Activating Token Index: 46

Text #1

Max Range: 3.0444. Min Range: -3.0444

Max Act: 2.9937. Min Act: -0.0000

Data Index: 1355082 (C4 (Web Text))

Max Activating Token Index: 900

Text #2

Max Range: 3.0444. Min Range: -3.0444

Max Act: 2.8343. Min Act: -0.0000

Data Index: 181724 (C4 (Web Text))

Max Activating Token Index: 448

Text #3

Max Range: 3.0444. Min Range: -3.0444

Max Act: 2.5596. Min Act: -0.0000

Data Index: 886303 (C4 (Web Text))

Max Activating Token Index: 589

Text #4

Max Range: 3.0444. Min Range: -3.0444

Max Act: 2.6059. Min Act: -0.0000

Data Index: 337875 (C4 (Web Text))

Max Activating Token Index: 685

Text #5

Max Range: 3.0444. Min Range: -3.0444

Max Act: 2.6116. Min Act: -0.0000

Data Index: 373914 (C4 (Web Text))

Max Activating Token Index: 765

Text #6

Max Range: 3.0444. Min Range: -3.0444

Max Act: 2.3465. Min Act: -0.0000

Data Index: 627934 (C4 (Web Text))

Max Activating Token Index: 597

Text #7

Max Range: 3.0444. Min Range: -3.0444

Max Act: 2.4342. Min Act: -0.0000

Data Index: 63566 (C4 (Web Text))

Max Activating Token Index: 914

Text #8

Max Range: 3.0444. Min Range: -3.0444

Max Act: 2.4198. Min Act: -0.0000

Data Index: 1319973 (C4 (Web Text))

Max Activating Token Index: 819

Text #9

Max Range: 3.0444. Min Range: -3.0444

Max Act: 2.3975. Min Act: -0.0000

Data Index: 12827 (C4 (Web Text))

Max Activating Token Index: 50

Text #10

Max Range: 3.0444. Min Range: -3.0444

Max Act: 2.4075. Min Act: -0.0000

Data Index: 1282165 (C4 (Web Text))

Max Activating Token Index: 998

Text #11

Max Range: 3.0444. Min Range: -3.0444

Max Act: 2.2255. Min Act: -0.0000

Data Index: 587071 (C4 (Web Text))

Max Activating Token Index: 884

Text #12

Max Range: 3.0444. Min Range: -3.0444

Max Act: 2.3297. Min Act: -0.0000

Data Index: 733931 (C4 (Web Text))

Max Activating Token Index: 244

Text #13

Max Range: 3.0444. Min Range: -3.0444

Max Act: 2.4085. Min Act: -0.0000

Data Index: 78231 (C4 (Web Text))

Max Activating Token Index: 930

Text #14

Max Range: 3.0444. Min Range: -3.0444

Max Act: 2.4263. Min Act: -0.0000

Data Index: 1208260 (C4 (Web Text))

Max Activating Token Index: 336

Text #15

Max Range: 3.0444. Min Range: -3.0444

Max Act: 2.3866. Min Act: -0.0000

Data Index: 262004 (C4 (Web Text))

Max Activating Token Index: 786

Text #16

Max Range: 3.0444. Min Range: -3.0444

Max Act: 2.3570. Min Act: -0.0000

Data Index: 1204232 (C4 (Web Text))

Max Activating Token Index: 884

Text #17

Max Range: 3.0444. Min Range: -3.0444

Max Act: 2.4501. Min Act: -0.0000

Data Index: 306902 (C4 (Web Text))

Max Activating Token Index: 232

Text #18

Max Range: 3.0444. Min Range: -3.0444

Max Act: 1.9785. Min Act: -0.0000

Data Index: 822097 (C4 (Web Text))

Max Activating Token Index: 144

Text #19

Max Range: 3.0444. Min Range: -3.0444

Max Act: 2.1598. Min Act: -0.0000

Data Index: 219557 (C4 (Web Text))

Max Activating Token Index: 982