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

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

Neuron 1816 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 2.3242. Min Range: -2.3242

Max Act: 2.3242. Min Act: -0.0002

Data Index: 852083 (C4 (Web Text))

Max Activating Token Index: 819

Text #1

Max Range: 2.3242. Min Range: -2.3242

Max Act: 2.2966. Min Act: -0.0002

Data Index: 1220791 (C4 (Web Text))

Max Activating Token Index: 587

Text #2

Max Range: 2.3242. Min Range: -2.3242

Max Act: 2.2341. Min Act: -0.0002

Data Index: 25312 (C4 (Web Text))

Max Activating Token Index: 705

Text #3

Max Range: 2.3242. Min Range: -2.3242

Max Act: 2.2765. Min Act: -0.0002

Data Index: 397777 (C4 (Web Text))

Max Activating Token Index: 482

Text #4

Max Range: 2.3242. Min Range: -2.3242

Max Act: 2.2505. Min Act: -0.0002

Data Index: 340246 (C4 (Web Text))

Max Activating Token Index: 677

Text #5

Max Range: 2.3242. Min Range: -2.3242

Max Act: 2.1041. Min Act: -0.0002

Data Index: 331506 (C4 (Web Text))

Max Activating Token Index: 576

Text #6

Max Range: 2.3242. Min Range: -2.3242

Max Act: 2.1580. Min Act: -0.0002

Data Index: 275787 (C4 (Web Text))

Max Activating Token Index: 780

Text #7

Max Range: 2.3242. Min Range: -2.3242

Max Act: 2.1658. Min Act: -0.0002

Data Index: 829862 (C4 (Web Text))

Max Activating Token Index: 318

Text #8

Max Range: 2.3242. Min Range: -2.3242

Max Act: 2.1454. Min Act: -0.0003

Data Index: 830522 (C4 (Web Text))

Max Activating Token Index: 617

Text #9

Max Range: 2.3242. Min Range: -2.3242

Max Act: 2.1528. Min Act: -0.0002

Data Index: 265773 (C4 (Web Text))

Max Activating Token Index: 175

Text #10

Max Range: 2.3242. Min Range: -2.3242

Max Act: 2.1018. Min Act: -0.0002

Data Index: 820423 (C4 (Web Text))

Max Activating Token Index: 479

Text #11

Max Range: 2.3242. Min Range: -2.3242

Max Act: 2.0648. Min Act: -0.0002

Data Index: 673005 (C4 (Web Text))

Max Activating Token Index: 9

Text #12

Max Range: 2.3242. Min Range: -2.3242

Max Act: 2.0466. Min Act: -0.0002

Data Index: 516405 (C4 (Web Text))

Max Activating Token Index: 736

Text #13

Max Range: 2.3242. Min Range: -2.3242

Max Act: 2.0645. Min Act: -0.0002

Data Index: 601543 (C4 (Web Text))

Max Activating Token Index: 922

Text #14

Max Range: 2.3242. Min Range: -2.3242

Max Act: 2.1247. Min Act: -0.0002

Data Index: 1315972 (C4 (Web Text))

Max Activating Token Index: 795

Text #15

Max Range: 2.3242. Min Range: -2.3242

Max Act: 1.9961. Min Act: -0.0002

Data Index: 57858 (C4 (Web Text))

Max Activating Token Index: 525

Text #16

Max Range: 2.3242. Min Range: -2.3242

Max Act: 2.0436. Min Act: -0.0002

Data Index: 754235 (C4 (Web Text))

Max Activating Token Index: 866

Text #17

Max Range: 2.3242. Min Range: -2.3242

Max Act: 2.0379. Min Act: -0.0002

Data Index: 817441 (C4 (Web Text))

Max Activating Token Index: 535

Text #18

Max Range: 2.3242. Min Range: -2.3242

Max Act: 2.0250. Min Act: -0.0002

Data Index: 458490 (C4 (Web Text))

Max Activating Token Index: 686

Text #19

Max Range: 2.3242. Min Range: -2.3242

Max Act: 2.0007. Min Act: -0.0002

Data Index: 710909 (C4 (Web Text))

Max Activating Token Index: 608