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

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

Neuron 3603 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: 1.7255. Min Range: -1.7255

Max Act: 1.5364. Min Act: -0.0000

Data Index: 280713 (C4 (Web Text))

Max Activating Token Index: 290

Text #1

Max Range: 1.7255. Min Range: -1.7255

Max Act: 1.6152. Min Act: -0.0000

Data Index: 1310944 (C4 (Web Text))

Max Activating Token Index: 288

Text #2

Max Range: 1.7255. Min Range: -1.7255

Max Act: 1.7255. Min Act: -0.0000

Data Index: 196056 (C4 (Web Text))

Max Activating Token Index: 257

Text #3

Max Range: 1.7255. Min Range: -1.7255

Max Act: 1.6285. Min Act: -0.0000

Data Index: 901749 (C4 (Web Text))

Max Activating Token Index: 290

Text #4

Max Range: 1.7255. Min Range: -1.7255

Max Act: 1.5448. Min Act: -0.0000

Data Index: 212838 (C4 (Web Text))

Max Activating Token Index: 716

Text #5

Max Range: 1.7255. Min Range: -1.7255

Max Act: 1.4944. Min Act: -0.0000

Data Index: 580847 (C4 (Web Text))

Max Activating Token Index: 574

Text #6

Max Range: 1.7255. Min Range: -1.7255

Max Act: 1.4341. Min Act: -0.0000

Data Index: 1002459 (C4 (Web Text))

Max Activating Token Index: 850

Text #7

Max Range: 1.7255. Min Range: -1.7255

Max Act: 1.3966. Min Act: -0.0001

Data Index: 193977 (C4 (Web Text))

Max Activating Token Index: 455

Text #8

Max Range: 1.7255. Min Range: -1.7255

Max Act: 1.3703. Min Act: -0.0000

Data Index: 884307 (C4 (Web Text))

Max Activating Token Index: 143

Text #9

Max Range: 1.7255. Min Range: -1.7255

Max Act: 1.3879. Min Act: -0.0001

Data Index: 1180355 (C4 (Web Text))

Max Activating Token Index: 849

Text #10

Max Range: 1.7255. Min Range: -1.7255

Max Act: 1.3399. Min Act: -0.0000

Data Index: 1244526 (C4 (Web Text))

Max Activating Token Index: 15

Text #11

Max Range: 1.7255. Min Range: -1.7255

Max Act: 1.3345. Min Act: -0.0000

Data Index: 128172 (C4 (Web Text))

Max Activating Token Index: 595

Text #12

Max Range: 1.7255. Min Range: -1.7255

Max Act: 1.2847. Min Act: -0.0000

Data Index: 74838 (C4 (Web Text))

Max Activating Token Index: 842

Text #13

Max Range: 1.7255. Min Range: -1.7255

Max Act: 1.2654. Min Act: -0.0000

Data Index: 304747 (C4 (Web Text))

Max Activating Token Index: 364

Text #14

Max Range: 1.7255. Min Range: -1.7255

Max Act: 1.3375. Min Act: -0.0001

Data Index: 965586 (C4 (Web Text))

Max Activating Token Index: 531

Text #15

Max Range: 1.7255. Min Range: -1.7255

Max Act: 1.3019. Min Act: -0.0001

Data Index: 424429 (C4 (Web Text))

Max Activating Token Index: 947

Text #16

Max Range: 1.7255. Min Range: -1.7255

Max Act: 1.2423. Min Act: -0.0000

Data Index: 568329 (C4 (Web Text))

Max Activating Token Index: 84

Text #17

Max Range: 1.7255. Min Range: -1.7255

Max Act: 1.2684. Min Act: -0.0001

Data Index: 167889 (C4 (Web Text))

Max Activating Token Index: 796

Text #18

Max Range: 1.7255. Min Range: -1.7255

Max Act: 1.2029. Min Act: -0.0001

Data Index: 766309 (C4 (Web Text))

Max Activating Token Index: 840

Text #19

Max Range: 1.7255. Min Range: -1.7255

Max Act: 1.1817. Min Act: -0.0000

Data Index: 713961 (C4 (Web Text))

Max Activating Token Index: 821