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

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

Neuron 1416 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: 0.2891. Min Range: -0.2891

Max Act: 0.2891. Min Act: -0.0000

Data Index: 1231365 (C4 (Web Text))

Max Activating Token Index: 681

Text #1

Max Range: 0.2891. Min Range: -0.2891

Max Act: 0.2833. Min Act: -0.0000

Data Index: 1289748 (C4 (Web Text))

Max Activating Token Index: 594

Text #2

Max Range: 0.2891. Min Range: -0.2891

Max Act: 0.2836. Min Act: -0.0000

Data Index: 761284 (C4 (Web Text))

Max Activating Token Index: 148

Text #3

Max Range: 0.2891. Min Range: -0.2891

Max Act: 0.2559. Min Act: -0.0000

Data Index: 1054123 (C4 (Web Text))

Max Activating Token Index: 845

Text #4

Max Range: 0.2891. Min Range: -0.2891

Max Act: 0.2454. Min Act: -0.0000

Data Index: 266088 (C4 (Web Text))

Max Activating Token Index: 199

Text #5

Max Range: 0.2891. Min Range: -0.2891

Max Act: 0.2482. Min Act: -0.0000

Data Index: 777445 (C4 (Web Text))

Max Activating Token Index: 438

Text #6

Max Range: 0.2891. Min Range: -0.2891

Max Act: 0.2357. Min Act: -0.0000

Data Index: 1081736 (C4 (Web Text))

Max Activating Token Index: 154

Text #7

Max Range: 0.2891. Min Range: -0.2891

Max Act: 0.2343. Min Act: -0.0000

Data Index: 73844 (C4 (Web Text))

Max Activating Token Index: 421

Text #8

Max Range: 0.2891. Min Range: -0.2891

Max Act: 0.2434. Min Act: -0.0000

Data Index: 356168 (C4 (Web Text))

Max Activating Token Index: 57

Text #9

Max Range: 0.2891. Min Range: -0.2891

Max Act: 0.2571. Min Act: -0.0000

Data Index: 1168053 (C4 (Web Text))

Max Activating Token Index: 224

Text #10

Max Range: 0.2891. Min Range: -0.2891

Max Act: 0.2157. Min Act: -0.0000

Data Index: 200636 (C4 (Web Text))

Max Activating Token Index: 243

Text #11

Max Range: 0.2891. Min Range: -0.2891

Max Act: 0.2486. Min Act: -0.0000

Data Index: 425379 (C4 (Web Text))

Max Activating Token Index: 645

Text #12

Max Range: 0.2891. Min Range: -0.2891

Max Act: 0.2221. Min Act: -0.0000

Data Index: 1245944 (C4 (Web Text))

Max Activating Token Index: 95

Text #13

Max Range: 0.2891. Min Range: -0.2891

Max Act: 0.2389. Min Act: -0.0000

Data Index: 907741 (C4 (Web Text))

Max Activating Token Index: 821

Text #14

Max Range: 0.2891. Min Range: -0.2891

Max Act: 0.2378. Min Act: -0.0000

Data Index: 499690 (C4 (Web Text))

Max Activating Token Index: 671

Text #15

Max Range: 0.2891. Min Range: -0.2891

Max Act: 0.2459. Min Act: -0.0000

Data Index: 185034 (C4 (Web Text))

Max Activating Token Index: 174

Text #16

Max Range: 0.2891. Min Range: -0.2891

Max Act: 0.2366. Min Act: -0.0000

Data Index: 1113659 (C4 (Web Text))

Max Activating Token Index: 620

Text #17

Max Range: 0.2891. Min Range: -0.2891

Max Act: 0.2464. Min Act: -0.0000

Data Index: 265302 (C4 (Web Text))

Max Activating Token Index: 39

Text #18

Max Range: 0.2891. Min Range: -0.2891

Max Act: 0.2389. Min Act: -0.0000

Data Index: 964685 (C4 (Web Text))

Max Activating Token Index: 721

Text #19

Max Range: 0.2891. Min Range: -0.2891

Max Act: 0.2281. Min Act: -0.0000

Data Index: 278237 (C4 (Web Text))

Max Activating Token Index: 289