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

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

Neuron 2615 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6871. Min Range: -0.6871

Max Act: 0.6871. Min Act: -0.0001

Data Index: 642293 (C4 (Web Text))

Max Activating Token Index: 866

Text #1

Max Range: 0.6871. Min Range: -0.6871

Max Act: 0.6750. Min Act: -0.0001

Data Index: 138637 (C4 (Web Text))

Max Activating Token Index: 628

Text #2

Max Range: 0.6871. Min Range: -0.6871

Max Act: 0.6641. Min Act: -0.0001

Data Index: 251427 (C4 (Web Text))

Max Activating Token Index: 8

Text #3

Max Range: 0.6871. Min Range: -0.6871

Max Act: 0.6283. Min Act: -0.0001

Data Index: 178069 (C4 (Web Text))

Max Activating Token Index: 210

Text #4

Max Range: 0.6871. Min Range: -0.6871

Max Act: 0.6639. Min Act: -0.0001

Data Index: 1068392 (C4 (Web Text))

Max Activating Token Index: 268

Text #5

Max Range: 0.6871. Min Range: -0.6871

Max Act: 0.6345. Min Act: -0.0001

Data Index: 762153 (C4 (Web Text))

Max Activating Token Index: 644

Text #6

Max Range: 0.6871. Min Range: -0.6871

Max Act: 0.6476. Min Act: -0.0001

Data Index: 472200 (C4 (Web Text))

Max Activating Token Index: 47

Text #7

Max Range: 0.6871. Min Range: -0.6871

Max Act: 0.6106. Min Act: -0.0001

Data Index: 989990 (C4 (Web Text))

Max Activating Token Index: 178

Text #8

Max Range: 0.6871. Min Range: -0.6871

Max Act: 0.5929. Min Act: -0.0001

Data Index: 5296 (C4 (Web Text))

Max Activating Token Index: 434

Text #9

Max Range: 0.6871. Min Range: -0.6871

Max Act: 0.5859. Min Act: -0.0001

Data Index: 846019 (C4 (Web Text))

Max Activating Token Index: 980

Text #10

Max Range: 0.6871. Min Range: -0.6871

Max Act: 0.5920. Min Act: -0.0001

Data Index: 282799 (C4 (Web Text))

Max Activating Token Index: 434

Text #11

Max Range: 0.6871. Min Range: -0.6871

Max Act: 0.6060. Min Act: -0.0001

Data Index: 601330 (C4 (Web Text))

Max Activating Token Index: 415

Text #12

Max Range: 0.6871. Min Range: -0.6871

Max Act: 0.6174. Min Act: -0.0001

Data Index: 465260 (C4 (Web Text))

Max Activating Token Index: 466

Text #13

Max Range: 0.6871. Min Range: -0.6871

Max Act: 0.5676. Min Act: -0.0001

Data Index: 609319 (C4 (Web Text))

Max Activating Token Index: 481

Text #14

Max Range: 0.6871. Min Range: -0.6871

Max Act: 0.6126. Min Act: -0.0001

Data Index: 1304644 (C4 (Web Text))

Max Activating Token Index: 195

Text #15

Max Range: 0.6871. Min Range: -0.6871

Max Act: 0.5787. Min Act: -0.0001

Data Index: 792220 (C4 (Web Text))

Max Activating Token Index: 458

Text #16

Max Range: 0.6871. Min Range: -0.6871

Max Act: 0.5941. Min Act: -0.0001

Data Index: 3746 (C4 (Web Text))

Max Activating Token Index: 590

Text #17

Max Range: 0.6871. Min Range: -0.6871

Max Act: 0.5925. Min Act: -0.0001

Data Index: 543869 (C4 (Web Text))

Max Activating Token Index: 115

Text #18

Max Range: 0.6871. Min Range: -0.6871

Max Act: 0.5275. Min Act: -0.0001

Data Index: 281270 (C4 (Web Text))

Max Activating Token Index: 650

Text #19

Max Range: 0.6871. Min Range: -0.6871

Max Act: 0.5754. Min Act: -0.0001

Data Index: 193493 (C4 (Web Text))

Max Activating Token Index: 241