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

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

Neuron 2071 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8543. Min Range: -1.8543

Max Act: 1.8543. Min Act: -0.0000

Data Index: 1234395 (C4 (Web Text))

Max Activating Token Index: 467

Text #1

Max Range: 1.8543. Min Range: -1.8543

Max Act: 1.8034. Min Act: -0.0000

Data Index: 840823 (C4 (Web Text))

Max Activating Token Index: 599

Text #2

Max Range: 1.8543. Min Range: -1.8543

Max Act: 1.5313. Min Act: -0.0000

Data Index: 961011 (C4 (Web Text))

Max Activating Token Index: 79

Text #3

Max Range: 1.8543. Min Range: -1.8543

Max Act: 1.6448. Min Act: -0.0000

Data Index: 516454 (C4 (Web Text))

Max Activating Token Index: 453

Text #4

Max Range: 1.8543. Min Range: -1.8543

Max Act: 1.5349. Min Act: -0.0001

Data Index: 1204197 (C4 (Web Text))

Max Activating Token Index: 747

Text #5

Max Range: 1.8543. Min Range: -1.8543

Max Act: 1.6095. Min Act: -0.0000

Data Index: 1233178 (C4 (Web Text))

Max Activating Token Index: 324

Text #6

Max Range: 1.8543. Min Range: -1.8543

Max Act: 1.5062. Min Act: -0.0000

Data Index: 823312 (C4 (Web Text))

Max Activating Token Index: 327

Text #7

Max Range: 1.8543. Min Range: -1.8543

Max Act: 1.5018. Min Act: -0.0000

Data Index: 660805 (C4 (Web Text))

Max Activating Token Index: 127

Text #8

Max Range: 1.8543. Min Range: -1.8543

Max Act: 1.5058. Min Act: -0.0000

Data Index: 255446 (C4 (Web Text))

Max Activating Token Index: 613

Text #9

Max Range: 1.8543. Min Range: -1.8543

Max Act: 1.5008. Min Act: -0.0000

Data Index: 1281488 (C4 (Web Text))

Max Activating Token Index: 487

Text #10

Max Range: 1.8543. Min Range: -1.8543

Max Act: 1.5302. Min Act: -0.0000

Data Index: 551205 (C4 (Web Text))

Max Activating Token Index: 680

Text #11

Max Range: 1.8543. Min Range: -1.8543

Max Act: 1.4431. Min Act: -0.0001

Data Index: 337660 (C4 (Web Text))

Max Activating Token Index: 290

Text #12

Max Range: 1.8543. Min Range: -1.8543

Max Act: 1.4704. Min Act: -0.0000

Data Index: 47904 (C4 (Web Text))

Max Activating Token Index: 411

Text #13

Max Range: 1.8543. Min Range: -1.8543

Max Act: 1.4514. Min Act: -0.0000

Data Index: 89467 (C4 (Web Text))

Max Activating Token Index: 551

Text #14

Max Range: 1.8543. Min Range: -1.8543

Max Act: 1.3994. Min Act: -0.0000

Data Index: 260066 (C4 (Web Text))

Max Activating Token Index: 831

Text #15

Max Range: 1.8543. Min Range: -1.8543

Max Act: 1.5338. Min Act: -0.0000

Data Index: 1081121 (C4 (Web Text))

Max Activating Token Index: 570

Text #16

Max Range: 1.8543. Min Range: -1.8543

Max Act: 1.3960. Min Act: -0.0000

Data Index: 612745 (C4 (Web Text))

Max Activating Token Index: 498

Text #17

Max Range: 1.8543. Min Range: -1.8543

Max Act: 1.4387. Min Act: -0.0000

Data Index: 816736 (C4 (Web Text))

Max Activating Token Index: 480

Text #18

Max Range: 1.8543. Min Range: -1.8543

Max Act: 1.4277. Min Act: -0.0000

Data Index: 762554 (C4 (Web Text))

Max Activating Token Index: 991

Text #19

Max Range: 1.8543. Min Range: -1.8543

Max Act: 1.2805. Min Act: -0.0000

Data Index: 96834 (C4 (Web Text))

Max Activating Token Index: 684