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

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

Neuron 4591 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4137. Min Range: -1.4137

Max Act: 1.4137. Min Act: -0.0000

Data Index: 40564 (C4 (Web Text))

Max Activating Token Index: 228

Text #1

Max Range: 1.4137. Min Range: -1.4137

Max Act: 1.3349. Min Act: -0.0000

Data Index: 63317 (C4 (Web Text))

Max Activating Token Index: 951

Text #2

Max Range: 1.4137. Min Range: -1.4137

Max Act: 1.2955. Min Act: -0.0000

Data Index: 1329022 (C4 (Web Text))

Max Activating Token Index: 590

Text #3

Max Range: 1.4137. Min Range: -1.4137

Max Act: 1.2306. Min Act: -0.0000

Data Index: 1099851 (C4 (Web Text))

Max Activating Token Index: 943

Text #4

Max Range: 1.4137. Min Range: -1.4137

Max Act: 1.2464. Min Act: -0.0000

Data Index: 19689 (C4 (Web Text))

Max Activating Token Index: 350

Text #5

Max Range: 1.4137. Min Range: -1.4137

Max Act: 1.2360. Min Act: -0.0000

Data Index: 535017 (C4 (Web Text))

Max Activating Token Index: 682

Text #6

Max Range: 1.4137. Min Range: -1.4137

Max Act: 1.2233. Min Act: -0.0000

Data Index: 532270 (C4 (Web Text))

Max Activating Token Index: 1017

Text #7

Max Range: 1.4137. Min Range: -1.4137

Max Act: 1.1884. Min Act: -0.0000

Data Index: 952836 (C4 (Web Text))

Max Activating Token Index: 575

Text #8

Max Range: 1.4137. Min Range: -1.4137

Max Act: 1.2117. Min Act: -0.0000

Data Index: 797659 (C4 (Web Text))

Max Activating Token Index: 389

Text #9

Max Range: 1.4137. Min Range: -1.4137

Max Act: 1.1368. Min Act: -0.0000

Data Index: 1215487 (C4 (Web Text))

Max Activating Token Index: 149

Text #10

Max Range: 1.4137. Min Range: -1.4137

Max Act: 1.1601. Min Act: -0.0000

Data Index: 598836 (C4 (Web Text))

Max Activating Token Index: 50

Text #11

Max Range: 1.4137. Min Range: -1.4137

Max Act: 1.2230. Min Act: -0.0000

Data Index: 28792 (C4 (Web Text))

Max Activating Token Index: 1013

Text #12

Max Range: 1.4137. Min Range: -1.4137

Max Act: 1.0756. Min Act: -0.0000

Data Index: 710937 (C4 (Web Text))

Max Activating Token Index: 970

Text #13

Max Range: 1.4137. Min Range: -1.4137

Max Act: 1.1314. Min Act: -0.0000

Data Index: 266494 (C4 (Web Text))

Max Activating Token Index: 364

Text #14

Max Range: 1.4137. Min Range: -1.4137

Max Act: 1.1236. Min Act: -0.0000

Data Index: 1150993 (C4 (Web Text))

Max Activating Token Index: 829

Text #15

Max Range: 1.4137. Min Range: -1.4137

Max Act: 1.0911. Min Act: -0.0000

Data Index: 1156874 (C4 (Web Text))

Max Activating Token Index: 349

Text #16

Max Range: 1.4137. Min Range: -1.4137

Max Act: 1.0482. Min Act: 0.0001

Data Index: 1058262 (C4 (Web Text))

Max Activating Token Index: 678

Text #17

Max Range: 1.4137. Min Range: -1.4137

Max Act: 1.1111. Min Act: -0.0000

Data Index: 1033333 (C4 (Web Text))

Max Activating Token Index: 464

Text #18

Max Range: 1.4137. Min Range: -1.4137

Max Act: 1.1594. Min Act: -0.0000

Data Index: 502668 (C4 (Web Text))

Max Activating Token Index: 135

Text #19

Max Range: 1.4137. Min Range: -1.4137

Max Act: 1.2282. Min Act: -0.0000

Data Index: 1331643 (C4 (Web Text))

Max Activating Token Index: 652