Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1253 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 3.5514. Min Range: -3.5514

Max Act: 3.5514. Min Act: -0.0002

Data Index: 1147682 (C4 (Web Text))

Max Activating Token Index: 311

Text #1

Max Range: 3.5514. Min Range: -3.5514

Max Act: 3.4075. Min Act: -0.0002

Data Index: 693881 (C4 (Web Text))

Max Activating Token Index: 240

Text #2

Max Range: 3.5514. Min Range: -3.5514

Max Act: 3.2541. Min Act: -0.0002

Data Index: 809643 (C4 (Web Text))

Max Activating Token Index: 83

Text #3

Max Range: 3.5514. Min Range: -3.5514

Max Act: 3.0106. Min Act: -0.0002

Data Index: 990415 (C4 (Web Text))

Max Activating Token Index: 882

Text #4

Max Range: 3.5514. Min Range: -3.5514

Max Act: 3.0496. Min Act: -0.0002

Data Index: 1229932 (C4 (Web Text))

Max Activating Token Index: 327

Text #5

Max Range: 3.5514. Min Range: -3.5514

Max Act: 2.7537. Min Act: -0.0002

Data Index: 209574 (C4 (Web Text))

Max Activating Token Index: 203

Text #6

Max Range: 3.5514. Min Range: -3.5514

Max Act: 2.8121. Min Act: -0.0002

Data Index: 1306408 (C4 (Web Text))

Max Activating Token Index: 302

Text #7

Max Range: 3.5514. Min Range: -3.5514

Max Act: 2.6793. Min Act: -0.0002

Data Index: 699647 (C4 (Web Text))

Max Activating Token Index: 212

Text #8

Max Range: 3.5514. Min Range: -3.5514

Max Act: 2.7799. Min Act: -0.0002

Data Index: 1235473 (C4 (Web Text))

Max Activating Token Index: 122

Text #9

Max Range: 3.5514. Min Range: -3.5514

Max Act: 2.2793. Min Act: -0.0002

Data Index: 3655 (C4 (Web Text))

Max Activating Token Index: 724

Text #10

Max Range: 3.5514. Min Range: -3.5514

Max Act: 2.2767. Min Act: -0.0002

Data Index: 1247977 (C4 (Web Text))

Max Activating Token Index: 661

Text #11

Max Range: 3.5514. Min Range: -3.5514

Max Act: 2.8647. Min Act: -0.0002

Data Index: 170009 (C4 (Web Text))

Max Activating Token Index: 350

Text #12

Max Range: 3.5514. Min Range: -3.5514

Max Act: 2.4519. Min Act: -0.0002

Data Index: 1268941 (C4 (Web Text))

Max Activating Token Index: 746

Text #13

Max Range: 3.5514. Min Range: -3.5514

Max Act: 2.5175. Min Act: -0.0002

Data Index: 898072 (C4 (Web Text))

Max Activating Token Index: 24

Text #14

Max Range: 3.5514. Min Range: -3.5514

Max Act: 2.4983. Min Act: -0.0002

Data Index: 1154228 (C4 (Web Text))

Max Activating Token Index: 997

Text #15

Max Range: 3.5514. Min Range: -3.5514

Max Act: 2.4915. Min Act: -0.0001

Data Index: 1180097 (C4 (Web Text))

Max Activating Token Index: 978

Text #16

Max Range: 3.5514. Min Range: -3.5514

Max Act: 2.2654. Min Act: -0.0002

Data Index: 116002 (C4 (Web Text))

Max Activating Token Index: 921

Text #17

Max Range: 3.5514. Min Range: -3.5514

Max Act: 2.6944. Min Act: -0.0002

Data Index: 515368 (C4 (Web Text))

Max Activating Token Index: 575

Text #18

Max Range: 3.5514. Min Range: -3.5514

Max Act: 2.4618. Min Act: -0.0002

Data Index: 984729 (C4 (Web Text))

Max Activating Token Index: 417

Text #19

Max Range: 3.5514. Min Range: -3.5514

Max Act: 2.3759. Min Act: -0.0002

Data Index: 850984 (C4 (Web Text))

Max Activating Token Index: 300