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

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

Neuron 4819 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7769. Min Range: -2.7769

Max Act: 2.7769. Min Act: -0.0000

Data Index: 687892 (C4 (Web Text))

Max Activating Token Index: 46

Text #1

Max Range: 2.7769. Min Range: -2.7769

Max Act: 2.4851. Min Act: -0.0000

Data Index: 552106 (C4 (Web Text))

Max Activating Token Index: 389

Text #2

Max Range: 2.7769. Min Range: -2.7769

Max Act: 2.0967. Min Act: -0.0000

Data Index: 900877 (C4 (Web Text))

Max Activating Token Index: 209

Text #3

Max Range: 2.7769. Min Range: -2.7769

Max Act: 1.9583. Min Act: -0.0000

Data Index: 530728 (C4 (Web Text))

Max Activating Token Index: 188

Text #4

Max Range: 2.7769. Min Range: -2.7769

Max Act: 1.9449. Min Act: -0.0000

Data Index: 1062029 (C4 (Web Text))

Max Activating Token Index: 326

Text #5

Max Range: 2.7769. Min Range: -2.7769

Max Act: 1.9059. Min Act: -0.0000

Data Index: 932973 (C4 (Web Text))

Max Activating Token Index: 58

Text #6

Max Range: 2.7769. Min Range: -2.7769

Max Act: 1.8200. Min Act: -0.0000

Data Index: 196761 (C4 (Web Text))

Max Activating Token Index: 388

Text #7

Max Range: 2.7769. Min Range: -2.7769

Max Act: 1.8722. Min Act: -0.0000

Data Index: 894200 (C4 (Web Text))

Max Activating Token Index: 724

Text #8

Max Range: 2.7769. Min Range: -2.7769

Max Act: 1.7395. Min Act: -0.0000

Data Index: 667376 (C4 (Web Text))

Max Activating Token Index: 316

Text #9

Max Range: 2.7769. Min Range: -2.7769

Max Act: 1.6485. Min Act: -0.0000

Data Index: 1310632 (C4 (Web Text))

Max Activating Token Index: 664

Text #10

Max Range: 2.7769. Min Range: -2.7769

Max Act: 1.6597. Min Act: -0.0000

Data Index: 1037556 (C4 (Web Text))

Max Activating Token Index: 795

Text #11

Max Range: 2.7769. Min Range: -2.7769

Max Act: 1.8028. Min Act: -0.0000

Data Index: 1234749 (C4 (Web Text))

Max Activating Token Index: 708

Text #12

Max Range: 2.7769. Min Range: -2.7769

Max Act: 1.6773. Min Act: -0.0000

Data Index: 25513 (C4 (Web Text))

Max Activating Token Index: 471

Text #13

Max Range: 2.7769. Min Range: -2.7769

Max Act: 1.8399. Min Act: -0.0000

Data Index: 500264 (C4 (Web Text))

Max Activating Token Index: 440

Text #14

Max Range: 2.7769. Min Range: -2.7769

Max Act: 1.6510. Min Act: -0.0000

Data Index: 121881 (C4 (Web Text))

Max Activating Token Index: 651

Text #15

Max Range: 2.7769. Min Range: -2.7769

Max Act: 1.7422. Min Act: -0.0000

Data Index: 953213 (C4 (Web Text))

Max Activating Token Index: 171

Text #16

Max Range: 2.7769. Min Range: -2.7769

Max Act: 1.6436. Min Act: -0.0000

Data Index: 831046 (C4 (Web Text))

Max Activating Token Index: 830

Text #17

Max Range: 2.7769. Min Range: -2.7769

Max Act: 1.6037. Min Act: -0.0000

Data Index: 640283 (C4 (Web Text))

Max Activating Token Index: 150

Text #18

Max Range: 2.7769. Min Range: -2.7769

Max Act: 1.5933. Min Act: -0.0000

Data Index: 353973 (C4 (Web Text))

Max Activating Token Index: 640

Text #19

Max Range: 2.7769. Min Range: -2.7769

Max Act: 1.7030. Min Act: -0.0000

Data Index: 1081166 (C4 (Web Text))

Max Activating Token Index: 793