Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 632 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.2765. Min Range: -1.2765

Max Act: 1.2765. Min Act: -0.0001

Data Index: 53629 (C4 (Web Text))

Max Activating Token Index: 510

Text #1

Max Range: 1.2765. Min Range: -1.2765

Max Act: 1.2599. Min Act: -0.0000

Data Index: 994158 (C4 (Web Text))

Max Activating Token Index: 986

Text #2

Max Range: 1.2765. Min Range: -1.2765

Max Act: 1.2403. Min Act: -0.0001

Data Index: 907457 (C4 (Web Text))

Max Activating Token Index: 274

Text #3

Max Range: 1.2765. Min Range: -1.2765

Max Act: 1.1437. Min Act: -0.0001

Data Index: 242200 (C4 (Web Text))

Max Activating Token Index: 520

Text #4

Max Range: 1.2765. Min Range: -1.2765

Max Act: 1.1568. Min Act: -0.0001

Data Index: 6107 (C4 (Web Text))

Max Activating Token Index: 949

Text #5

Max Range: 1.2765. Min Range: -1.2765

Max Act: 1.0887. Min Act: -0.0001

Data Index: 592230 (C4 (Web Text))

Max Activating Token Index: 783

Text #6

Max Range: 1.2765. Min Range: -1.2765

Max Act: 1.1446. Min Act: -0.0000

Data Index: 443668 (C4 (Web Text))

Max Activating Token Index: 71

Text #7

Max Range: 1.2765. Min Range: -1.2765

Max Act: 1.1415. Min Act: -0.0001

Data Index: 747316 (C4 (Web Text))

Max Activating Token Index: 252

Text #8

Max Range: 1.2765. Min Range: -1.2765

Max Act: 1.1347. Min Act: -0.0001

Data Index: 508103 (C4 (Web Text))

Max Activating Token Index: 426

Text #9

Max Range: 1.2765. Min Range: -1.2765

Max Act: 1.0648. Min Act: -0.0001

Data Index: 964320 (C4 (Web Text))

Max Activating Token Index: 88

Text #10

Max Range: 1.2765. Min Range: -1.2765

Max Act: 1.1536. Min Act: -0.0001

Data Index: 596952 (C4 (Web Text))

Max Activating Token Index: 88

Text #11

Max Range: 1.2765. Min Range: -1.2765

Max Act: 1.1100. Min Act: -0.0000

Data Index: 784606 (C4 (Web Text))

Max Activating Token Index: 922

Text #12

Max Range: 1.2765. Min Range: -1.2765

Max Act: 1.1066. Min Act: -0.0001

Data Index: 930176 (C4 (Web Text))

Max Activating Token Index: 547

Text #13

Max Range: 1.2765. Min Range: -1.2765

Max Act: 1.1028. Min Act: -0.0001

Data Index: 934712 (C4 (Web Text))

Max Activating Token Index: 74

Text #14

Max Range: 1.2765. Min Range: -1.2765

Max Act: 1.1014. Min Act: -0.0001

Data Index: 402878 (C4 (Web Text))

Max Activating Token Index: 295

Text #15

Max Range: 1.2765. Min Range: -1.2765

Max Act: 1.0582. Min Act: -0.0001

Data Index: 196286 (C4 (Web Text))

Max Activating Token Index: 491

Text #16

Max Range: 1.2765. Min Range: -1.2765

Max Act: 1.0444. Min Act: -0.0001

Data Index: 791692 (C4 (Web Text))

Max Activating Token Index: 39

Text #17

Max Range: 1.2765. Min Range: -1.2765

Max Act: 1.0674. Min Act: -0.0001

Data Index: 865514 (C4 (Web Text))

Max Activating Token Index: 472

Text #18

Max Range: 1.2765. Min Range: -1.2765

Max Act: 1.0360. Min Act: -0.0001

Data Index: 555130 (C4 (Web Text))

Max Activating Token Index: 455

Text #19

Max Range: 1.2765. Min Range: -1.2765

Max Act: 1.0360. Min Act: -0.0001

Data Index: 56220 (C4 (Web Text))

Max Activating Token Index: 732