Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1553 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0595. Min Act: -0.0005

Data Index: 678363 (C4 (Web Text))

Max Activating Token Index: 915

Text #1

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0621. Min Act: -0.0005

Data Index: 1329488 (C4 (Web Text))

Max Activating Token Index: 999

Text #2

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0566. Min Act: -0.0005

Data Index: 469087 (C4 (Web Text))

Max Activating Token Index: 188

Text #3

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0525. Min Act: -0.0005

Data Index: 746582 (C4 (Web Text))

Max Activating Token Index: 32

Text #4

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0507. Min Act: -0.0005

Data Index: 986738 (C4 (Web Text))

Max Activating Token Index: 329

Text #5

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0509. Min Act: -0.0005

Data Index: 151379 (C4 (Web Text))

Max Activating Token Index: 772

Text #6

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0477. Min Act: -0.0005

Data Index: 119359 (C4 (Web Text))

Max Activating Token Index: 543

Text #7

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0474. Min Act: -0.0005

Data Index: 1132114 (C4 (Web Text))

Max Activating Token Index: 612

Text #8

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0525. Min Act: -0.0005

Data Index: 311578 (C4 (Web Text))

Max Activating Token Index: 616

Text #9

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0510. Min Act: -0.0005

Data Index: 148655 (C4 (Web Text))

Max Activating Token Index: 175

Text #10

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0486. Min Act: -0.0005

Data Index: 1291654 (C4 (Web Text))

Max Activating Token Index: 437

Text #11

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0470. Min Act: -0.0005

Data Index: 899593 (C4 (Web Text))

Max Activating Token Index: 881

Text #12

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0510. Min Act: -0.0005

Data Index: 71046 (C4 (Web Text))

Max Activating Token Index: 812

Text #13

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0470. Min Act: -0.0005

Data Index: 1184102 (C4 (Web Text))

Max Activating Token Index: 829

Text #14

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0478. Min Act: -0.0005

Data Index: 956293 (C4 (Web Text))

Max Activating Token Index: 16

Text #15

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0474. Min Act: -0.0005

Data Index: 216112 (C4 (Web Text))

Max Activating Token Index: 953

Text #16

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0472. Min Act: -0.0005

Data Index: 1198229 (C4 (Web Text))

Max Activating Token Index: 253

Text #17

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0460. Min Act: -0.0005

Data Index: 677854 (C4 (Web Text))

Max Activating Token Index: 778

Text #18

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0467. Min Act: -0.0005

Data Index: 903078 (C4 (Web Text))

Max Activating Token Index: 685

Text #19

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0462. Min Act: -0.0005

Data Index: 1253082 (C4 (Web Text))

Max Activating Token Index: 455