Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2607 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.1410. Min Range: -1.1410

Max Act: 1.1410. Min Act: -0.0000

Data Index: 1444090 (Python Code)

Max Activating Token Index: 380

Text #1

Max Range: 1.1410. Min Range: -1.1410

Max Act: 1.0406. Min Act: -0.0000

Data Index: 295933 (C4 (Web Text))

Max Activating Token Index: 443

Text #2

Max Range: 1.1410. Min Range: -1.1410

Max Act: 1.0500. Min Act: -0.0000

Data Index: 359336 (C4 (Web Text))

Max Activating Token Index: 34

Text #3

Max Range: 1.1410. Min Range: -1.1410

Max Act: 0.9925. Min Act: -0.0000

Data Index: 511670 (C4 (Web Text))

Max Activating Token Index: 742

Text #4

Max Range: 1.1410. Min Range: -1.1410

Max Act: 0.9947. Min Act: -0.0000

Data Index: 847701 (C4 (Web Text))

Max Activating Token Index: 483

Text #5

Max Range: 1.1410. Min Range: -1.1410

Max Act: 1.0362. Min Act: -0.0000

Data Index: 833510 (C4 (Web Text))

Max Activating Token Index: 298

Text #6

Max Range: 1.1410. Min Range: -1.1410

Max Act: 0.9712. Min Act: -0.0000

Data Index: 513534 (C4 (Web Text))

Max Activating Token Index: 713

Text #7

Max Range: 1.1410. Min Range: -1.1410

Max Act: 1.0176. Min Act: -0.0000

Data Index: 1159966 (C4 (Web Text))

Max Activating Token Index: 89

Text #8

Max Range: 1.1410. Min Range: -1.1410

Max Act: 0.9809. Min Act: -0.0000

Data Index: 1009556 (C4 (Web Text))

Max Activating Token Index: 561

Text #9

Max Range: 1.1410. Min Range: -1.1410

Max Act: 0.9619. Min Act: -0.0000

Data Index: 1163062 (C4 (Web Text))

Max Activating Token Index: 566

Text #10

Max Range: 1.1410. Min Range: -1.1410

Max Act: 0.8965. Min Act: -0.0000

Data Index: 746080 (C4 (Web Text))

Max Activating Token Index: 440

Text #11

Max Range: 1.1410. Min Range: -1.1410

Max Act: 0.8951. Min Act: -0.0000

Data Index: 629483 (C4 (Web Text))

Max Activating Token Index: 46

Text #12

Max Range: 1.1410. Min Range: -1.1410

Max Act: 0.9541. Min Act: -0.0000

Data Index: 1244717 (C4 (Web Text))

Max Activating Token Index: 418

Text #13

Max Range: 1.1410. Min Range: -1.1410

Max Act: 0.9488. Min Act: -0.0000

Data Index: 906431 (C4 (Web Text))

Max Activating Token Index: 508

Text #14

Max Range: 1.1410. Min Range: -1.1410

Max Act: 0.9976. Min Act: -0.0000

Data Index: 912085 (C4 (Web Text))

Max Activating Token Index: 792

Text #15

Max Range: 1.1410. Min Range: -1.1410

Max Act: 0.9288. Min Act: -0.0000

Data Index: 1228461 (C4 (Web Text))

Max Activating Token Index: 568

Text #16

Max Range: 1.1410. Min Range: -1.1410

Max Act: 0.9281. Min Act: -0.0000

Data Index: 1229121 (C4 (Web Text))

Max Activating Token Index: 292

Text #17

Max Range: 1.1410. Min Range: -1.1410

Max Act: 0.9660. Min Act: -0.0000

Data Index: 1529594 (Python Code)

Max Activating Token Index: 560

Text #18

Max Range: 1.1410. Min Range: -1.1410

Max Act: 0.8764. Min Act: -0.0000

Data Index: 795216 (C4 (Web Text))

Max Activating Token Index: 561

Text #19

Max Range: 1.1410. Min Range: -1.1410

Max Act: 0.8517. Min Act: -0.0000

Data Index: 739019 (C4 (Web Text))

Max Activating Token Index: 918