Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3440 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.4344. Min Range: -1.4344

Max Act: 1.4344. Min Act: -0.0001

Data Index: 1097708 (C4 (Web Text))

Max Activating Token Index: 272

Text #1

Max Range: 1.4344. Min Range: -1.4344

Max Act: 1.1411. Min Act: -0.0001

Data Index: 337484 (C4 (Web Text))

Max Activating Token Index: 602

Text #2

Max Range: 1.4344. Min Range: -1.4344

Max Act: 1.0304. Min Act: -0.0001

Data Index: 17366 (C4 (Web Text))

Max Activating Token Index: 348

Text #3

Max Range: 1.4344. Min Range: -1.4344

Max Act: 1.0400. Min Act: -0.0001

Data Index: 1290528 (C4 (Web Text))

Max Activating Token Index: 89

Text #4

Max Range: 1.4344. Min Range: -1.4344

Max Act: 1.0120. Min Act: -0.0001

Data Index: 386869 (C4 (Web Text))

Max Activating Token Index: 147

Text #5

Max Range: 1.4344. Min Range: -1.4344

Max Act: 0.9669. Min Act: -0.0001

Data Index: 716040 (C4 (Web Text))

Max Activating Token Index: 697

Text #6

Max Range: 1.4344. Min Range: -1.4344

Max Act: 0.9835. Min Act: -0.0001

Data Index: 592944 (C4 (Web Text))

Max Activating Token Index: 44

Text #7

Max Range: 1.4344. Min Range: -1.4344

Max Act: 0.9811. Min Act: -0.0001

Data Index: 405615 (C4 (Web Text))

Max Activating Token Index: 839

Text #8

Max Range: 1.4344. Min Range: -1.4344

Max Act: 0.9730. Min Act: -0.0001

Data Index: 250101 (C4 (Web Text))

Max Activating Token Index: 173

Text #9

Max Range: 1.4344. Min Range: -1.4344

Max Act: 0.9664. Min Act: -0.0001

Data Index: 1230139 (C4 (Web Text))

Max Activating Token Index: 1001

Text #10

Max Range: 1.4344. Min Range: -1.4344

Max Act: 0.9528. Min Act: -0.0001

Data Index: 633556 (C4 (Web Text))

Max Activating Token Index: 859

Text #11

Max Range: 1.4344. Min Range: -1.4344

Max Act: 0.9202. Min Act: -0.0001

Data Index: 1034763 (C4 (Web Text))

Max Activating Token Index: 180

Text #12

Max Range: 1.4344. Min Range: -1.4344

Max Act: 0.8816. Min Act: -0.0001

Data Index: 52190 (C4 (Web Text))

Max Activating Token Index: 272

Text #13

Max Range: 1.4344. Min Range: -1.4344

Max Act: 0.9115. Min Act: -0.0001

Data Index: 920660 (C4 (Web Text))

Max Activating Token Index: 630

Text #14

Max Range: 1.4344. Min Range: -1.4344

Max Act: 0.9104. Min Act: -0.0001

Data Index: 444120 (C4 (Web Text))

Max Activating Token Index: 75

Text #15

Max Range: 1.4344. Min Range: -1.4344

Max Act: 0.9320. Min Act: -0.0001

Data Index: 409298 (C4 (Web Text))

Max Activating Token Index: 138

Text #16

Max Range: 1.4344. Min Range: -1.4344

Max Act: 0.9282. Min Act: -0.0001

Data Index: 1081312 (C4 (Web Text))

Max Activating Token Index: 489

Text #17

Max Range: 1.4344. Min Range: -1.4344

Max Act: 0.9215. Min Act: -0.0001

Data Index: 13965 (C4 (Web Text))

Max Activating Token Index: 63

Text #18

Max Range: 1.4344. Min Range: -1.4344

Max Act: 0.8661. Min Act: -0.0001

Data Index: 1054558 (C4 (Web Text))

Max Activating Token Index: 82

Text #19

Max Range: 1.4344. Min Range: -1.4344

Max Act: 0.9115. Min Act: -0.0001

Data Index: 386533 (C4 (Web Text))

Max Activating Token Index: 420