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

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

Neuron 796 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4197. Min Range: -0.4197

Max Act: 0.4056. Min Act: -0.0000

Data Index: 728576 (C4 (Web Text))

Max Activating Token Index: 720

Text #1

Max Range: 0.4197. Min Range: -0.4197

Max Act: 0.4071. Min Act: -0.0000

Data Index: 184256 (C4 (Web Text))

Max Activating Token Index: 678

Text #2

Max Range: 0.4197. Min Range: -0.4197

Max Act: 0.4176. Min Act: -0.0000

Data Index: 1332849 (C4 (Web Text))

Max Activating Token Index: 598

Text #3

Max Range: 0.4197. Min Range: -0.4197

Max Act: 0.4197. Min Act: -0.0000

Data Index: 37270 (C4 (Web Text))

Max Activating Token Index: 419

Text #4

Max Range: 0.4197. Min Range: -0.4197

Max Act: 0.3670. Min Act: -0.0000

Data Index: 880118 (C4 (Web Text))

Max Activating Token Index: 32

Text #5

Max Range: 0.4197. Min Range: -0.4197

Max Act: 0.3702. Min Act: -0.0000

Data Index: 1235174 (C4 (Web Text))

Max Activating Token Index: 522

Text #6

Max Range: 0.4197. Min Range: -0.4197

Max Act: 0.3695. Min Act: -0.0000

Data Index: 417283 (C4 (Web Text))

Max Activating Token Index: 63

Text #7

Max Range: 0.4197. Min Range: -0.4197

Max Act: 0.3645. Min Act: -0.0000

Data Index: 742277 (C4 (Web Text))

Max Activating Token Index: 808

Text #8

Max Range: 0.4197. Min Range: -0.4197

Max Act: 0.3641. Min Act: -0.0000

Data Index: 1335189 (C4 (Web Text))

Max Activating Token Index: 909

Text #9

Max Range: 0.4197. Min Range: -0.4197

Max Act: 0.3490. Min Act: -0.0000

Data Index: 995249 (C4 (Web Text))

Max Activating Token Index: 338

Text #10

Max Range: 0.4197. Min Range: -0.4197

Max Act: 0.3368. Min Act: -0.0000

Data Index: 763595 (C4 (Web Text))

Max Activating Token Index: 650

Text #11

Max Range: 0.4197. Min Range: -0.4197

Max Act: 0.3486. Min Act: -0.0000

Data Index: 921770 (C4 (Web Text))

Max Activating Token Index: 308

Text #12

Max Range: 0.4197. Min Range: -0.4197

Max Act: 0.3409. Min Act: -0.0000

Data Index: 753495 (C4 (Web Text))

Max Activating Token Index: 526

Text #13

Max Range: 0.4197. Min Range: -0.4197

Max Act: 0.3544. Min Act: -0.0000

Data Index: 582606 (C4 (Web Text))

Max Activating Token Index: 983

Text #14

Max Range: 0.4197. Min Range: -0.4197

Max Act: 0.3164. Min Act: -0.0000

Data Index: 1355944 (C4 (Web Text))

Max Activating Token Index: 77

Text #15

Max Range: 0.4197. Min Range: -0.4197

Max Act: 0.3370. Min Act: -0.0000

Data Index: 1235964 (C4 (Web Text))

Max Activating Token Index: 34

Text #16

Max Range: 0.4197. Min Range: -0.4197

Max Act: 0.3497. Min Act: -0.0000

Data Index: 618760 (C4 (Web Text))

Max Activating Token Index: 141

Text #17

Max Range: 0.4197. Min Range: -0.4197

Max Act: 0.3484. Min Act: -0.0000

Data Index: 1175862 (C4 (Web Text))

Max Activating Token Index: 67

Text #18

Max Range: 0.4197. Min Range: -0.4197

Max Act: 0.3275. Min Act: -0.0000

Data Index: 804293 (C4 (Web Text))

Max Activating Token Index: 179

Text #19

Max Range: 0.4197. Min Range: -0.4197

Max Act: 0.3400. Min Act: -0.0000

Data Index: 1093205 (C4 (Web Text))

Max Activating Token Index: 437