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

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

Neuron 3117 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2163. Min Range: -1.2163

Max Act: 1.1112. Min Act: -0.0000

Data Index: 154438 (C4 (Web Text))

Max Activating Token Index: 448

Text #1

Max Range: 1.2163. Min Range: -1.2163

Max Act: 1.2163. Min Act: -0.0000

Data Index: 831889 (C4 (Web Text))

Max Activating Token Index: 674

Text #2

Max Range: 1.2163. Min Range: -1.2163

Max Act: 1.1109. Min Act: 0.0000

Data Index: 355664 (C4 (Web Text))

Max Activating Token Index: 233

Text #3

Max Range: 1.2163. Min Range: -1.2163

Max Act: 1.0086. Min Act: -0.0000

Data Index: 533806 (C4 (Web Text))

Max Activating Token Index: 570

Text #4

Max Range: 1.2163. Min Range: -1.2163

Max Act: 0.9980. Min Act: -0.0000

Data Index: 386778 (C4 (Web Text))

Max Activating Token Index: 125

Text #5

Max Range: 1.2163. Min Range: -1.2163

Max Act: 0.9119. Min Act: -0.0000

Data Index: 74362 (C4 (Web Text))

Max Activating Token Index: 349

Text #6

Max Range: 1.2163. Min Range: -1.2163

Max Act: 0.9450. Min Act: -0.0000

Data Index: 1190606 (C4 (Web Text))

Max Activating Token Index: 730

Text #7

Max Range: 1.2163. Min Range: -1.2163

Max Act: 0.9341. Min Act: -0.0000

Data Index: 111461 (C4 (Web Text))

Max Activating Token Index: 536

Text #8

Max Range: 1.2163. Min Range: -1.2163

Max Act: 0.9295. Min Act: -0.0000

Data Index: 523494 (C4 (Web Text))

Max Activating Token Index: 809

Text #9

Max Range: 1.2163. Min Range: -1.2163

Max Act: 0.9206. Min Act: -0.0000

Data Index: 734040 (C4 (Web Text))

Max Activating Token Index: 65

Text #10

Max Range: 1.2163. Min Range: -1.2163

Max Act: 0.8875. Min Act: -0.0000

Data Index: 1197895 (C4 (Web Text))

Max Activating Token Index: 356

Text #11

Max Range: 1.2163. Min Range: -1.2163

Max Act: 0.8782. Min Act: -0.0000

Data Index: 1041996 (C4 (Web Text))

Max Activating Token Index: 819

Text #12

Max Range: 1.2163. Min Range: -1.2163

Max Act: 0.9031. Min Act: -0.0000

Data Index: 1153343 (C4 (Web Text))

Max Activating Token Index: 681

Text #13

Max Range: 1.2163. Min Range: -1.2163

Max Act: 0.8975. Min Act: -0.0000

Data Index: 39107 (C4 (Web Text))

Max Activating Token Index: 303

Text #14

Max Range: 1.2163. Min Range: -1.2163

Max Act: 0.9346. Min Act: -0.0000

Data Index: 966986 (C4 (Web Text))

Max Activating Token Index: 781

Text #15

Max Range: 1.2163. Min Range: -1.2163

Max Act: 0.9174. Min Act: -0.0000

Data Index: 435290 (C4 (Web Text))

Max Activating Token Index: 536

Text #16

Max Range: 1.2163. Min Range: -1.2163

Max Act: 0.8399. Min Act: -0.0000

Data Index: 776876 (C4 (Web Text))

Max Activating Token Index: 523

Text #17

Max Range: 1.2163. Min Range: -1.2163

Max Act: 0.8736. Min Act: -0.0000

Data Index: 948103 (C4 (Web Text))

Max Activating Token Index: 220

Text #18

Max Range: 1.2163. Min Range: -1.2163

Max Act: 0.8543. Min Act: -0.0000

Data Index: 555173 (C4 (Web Text))

Max Activating Token Index: 545

Text #19

Max Range: 1.2163. Min Range: -1.2163

Max Act: 0.8245. Min Act: -0.0000

Data Index: 1239505 (C4 (Web Text))

Max Activating Token Index: 168