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

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

Neuron 709 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4614. Min Range: -0.4614

Max Act: 0.4614. Min Act: -0.0000

Data Index: 666424 (C4 (Web Text))

Max Activating Token Index: 881

Text #1

Max Range: 0.4614. Min Range: -0.4614

Max Act: 0.4224. Min Act: -0.0000

Data Index: 39933 (C4 (Web Text))

Max Activating Token Index: 419

Text #2

Max Range: 0.4614. Min Range: -0.4614

Max Act: 0.3383. Min Act: -0.0000

Data Index: 317965 (C4 (Web Text))

Max Activating Token Index: 640

Text #3

Max Range: 0.4614. Min Range: -0.4614

Max Act: 0.3122. Min Act: -0.0000

Data Index: 152338 (C4 (Web Text))

Max Activating Token Index: 925

Text #4

Max Range: 0.4614. Min Range: -0.4614

Max Act: 0.3070. Min Act: -0.0000

Data Index: 345806 (C4 (Web Text))

Max Activating Token Index: 962

Text #5

Max Range: 0.4614. Min Range: -0.4614

Max Act: 0.3039. Min Act: -0.0000

Data Index: 1049361 (C4 (Web Text))

Max Activating Token Index: 663

Text #6

Max Range: 0.4614. Min Range: -0.4614

Max Act: 0.2978. Min Act: -0.0000

Data Index: 1337571 (C4 (Web Text))

Max Activating Token Index: 591

Text #7

Max Range: 0.4614. Min Range: -0.4614

Max Act: 0.3071. Min Act: -0.0000

Data Index: 189102 (C4 (Web Text))

Max Activating Token Index: 91

Text #8

Max Range: 0.4614. Min Range: -0.4614

Max Act: 0.2693. Min Act: -0.0000

Data Index: 661055 (C4 (Web Text))

Max Activating Token Index: 159

Text #9

Max Range: 0.4614. Min Range: -0.4614

Max Act: 0.2716. Min Act: -0.0000

Data Index: 12792 (C4 (Web Text))

Max Activating Token Index: 384

Text #10

Max Range: 0.4614. Min Range: -0.4614

Max Act: 0.2708. Min Act: -0.0000

Data Index: 966519 (C4 (Web Text))

Max Activating Token Index: 414

Text #11

Max Range: 0.4614. Min Range: -0.4614

Max Act: 0.2704. Min Act: -0.0000

Data Index: 460496 (C4 (Web Text))

Max Activating Token Index: 182

Text #12

Max Range: 0.4614. Min Range: -0.4614

Max Act: 0.2540. Min Act: -0.0000

Data Index: 860563 (C4 (Web Text))

Max Activating Token Index: 113

Text #13

Max Range: 0.4614. Min Range: -0.4614

Max Act: 0.2832. Min Act: -0.0000

Data Index: 797756 (C4 (Web Text))

Max Activating Token Index: 123

Text #14

Max Range: 0.4614. Min Range: -0.4614

Max Act: 0.2562. Min Act: -0.0000

Data Index: 1022741 (C4 (Web Text))

Max Activating Token Index: 664

Text #15

Max Range: 0.4614. Min Range: -0.4614

Max Act: 0.2547. Min Act: -0.0000

Data Index: 277258 (C4 (Web Text))

Max Activating Token Index: 524

Text #16

Max Range: 0.4614. Min Range: -0.4614

Max Act: 0.2504. Min Act: -0.0000

Data Index: 614352 (C4 (Web Text))

Max Activating Token Index: 340

Text #17

Max Range: 0.4614. Min Range: -0.4614

Max Act: 0.2561. Min Act: -0.0000

Data Index: 959154 (C4 (Web Text))

Max Activating Token Index: 410

Text #18

Max Range: 0.4614. Min Range: -0.4614

Max Act: 0.2700. Min Act: -0.0000

Data Index: 626840 (C4 (Web Text))

Max Activating Token Index: 1008

Text #19

Max Range: 0.4614. Min Range: -0.4614

Max Act: 0.2617. Min Act: -0.0000

Data Index: 184239 (C4 (Web Text))

Max Activating Token Index: 77