Model: SoLU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 462 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 0.0963. Min Range: -0.0963

Max Act: 0.0963. Min Act: -0.0003

Data Index: 853385 (C4 (Web Text))

Max Activating Token Index: 783

Text #1

Max Range: 0.0963. Min Range: -0.0963

Max Act: 0.0740. Min Act: -0.0003

Data Index: 926142 (C4 (Web Text))

Max Activating Token Index: 310

Text #2

Max Range: 0.0963. Min Range: -0.0963

Max Act: 0.0753. Min Act: -0.0003

Data Index: 1023005 (C4 (Web Text))

Max Activating Token Index: 261

Text #3

Max Range: 0.0963. Min Range: -0.0963

Max Act: 0.0753. Min Act: -0.0003

Data Index: 1351375 (C4 (Web Text))

Max Activating Token Index: 256

Text #4

Max Range: 0.0963. Min Range: -0.0963

Max Act: 0.0748. Min Act: -0.0003

Data Index: 375744 (C4 (Web Text))

Max Activating Token Index: 631

Text #5

Max Range: 0.0963. Min Range: -0.0963

Max Act: 0.0796. Min Act: -0.0003

Data Index: 418226 (C4 (Web Text))

Max Activating Token Index: 843

Text #6

Max Range: 0.0963. Min Range: -0.0963

Max Act: 0.0756. Min Act: -0.0003

Data Index: 1076856 (C4 (Web Text))

Max Activating Token Index: 400

Text #7

Max Range: 0.0963. Min Range: -0.0963

Max Act: 0.0736. Min Act: -0.0003

Data Index: 652705 (C4 (Web Text))

Max Activating Token Index: 761

Text #8

Max Range: 0.0963. Min Range: -0.0963

Max Act: 0.0737. Min Act: -0.0003

Data Index: 498546 (C4 (Web Text))

Max Activating Token Index: 226

Text #9

Max Range: 0.0963. Min Range: -0.0963

Max Act: 0.0697. Min Act: -0.0003

Data Index: 767312 (C4 (Web Text))

Max Activating Token Index: 1017

Text #10

Max Range: 0.0963. Min Range: -0.0963

Max Act: 0.0710. Min Act: -0.0003

Data Index: 1056978 (C4 (Web Text))

Max Activating Token Index: 705

Text #11

Max Range: 0.0963. Min Range: -0.0963

Max Act: 0.0688. Min Act: -0.0003

Data Index: 130065 (C4 (Web Text))

Max Activating Token Index: 272

Text #12

Max Range: 0.0963. Min Range: -0.0963

Max Act: 0.0721. Min Act: -0.0003

Data Index: 450356 (C4 (Web Text))

Max Activating Token Index: 773

Text #13

Max Range: 0.0963. Min Range: -0.0963

Max Act: 0.0685. Min Act: -0.0003

Data Index: 300552 (C4 (Web Text))

Max Activating Token Index: 144

Text #14

Max Range: 0.0963. Min Range: -0.0963

Max Act: 0.0674. Min Act: -0.0003

Data Index: 592694 (C4 (Web Text))

Max Activating Token Index: 734

Text #15

Max Range: 0.0963. Min Range: -0.0963

Max Act: 0.0676. Min Act: -0.0003

Data Index: 1186072 (C4 (Web Text))

Max Activating Token Index: 980

Text #16

Max Range: 0.0963. Min Range: -0.0963

Max Act: 0.0685. Min Act: -0.0003

Data Index: 334585 (C4 (Web Text))

Max Activating Token Index: 79

Text #17

Max Range: 0.0963. Min Range: -0.0963

Max Act: 0.0686. Min Act: -0.0003

Data Index: 702672 (C4 (Web Text))

Max Activating Token Index: 671

Text #18

Max Range: 0.0963. Min Range: -0.0963

Max Act: 0.0700. Min Act: -0.0003

Data Index: 626644 (C4 (Web Text))

Max Activating Token Index: 339

Text #19

Max Range: 0.0963. Min Range: -0.0963

Max Act: 0.0701. Min Act: -0.0003

Data Index: 300777 (C4 (Web Text))

Max Activating Token Index: 773