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

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

Neuron 4996 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1452. Min Range: -1.1452

Max Act: 1.1452. Min Act: -0.0002

Data Index: 556016 (C4 (Web Text))

Max Activating Token Index: 990

Text #1

Max Range: 1.1452. Min Range: -1.1452

Max Act: 1.0145. Min Act: -0.0002

Data Index: 678610 (C4 (Web Text))

Max Activating Token Index: 5

Text #2

Max Range: 1.1452. Min Range: -1.1452

Max Act: 1.0332. Min Act: -0.0002

Data Index: 369247 (C4 (Web Text))

Max Activating Token Index: 310

Text #3

Max Range: 1.1452. Min Range: -1.1452

Max Act: 0.9894. Min Act: -0.0002

Data Index: 451872 (C4 (Web Text))

Max Activating Token Index: 529

Text #4

Max Range: 1.1452. Min Range: -1.1452

Max Act: 0.9963. Min Act: -0.0002

Data Index: 1019501 (C4 (Web Text))

Max Activating Token Index: 473

Text #5

Max Range: 1.1452. Min Range: -1.1452

Max Act: 0.9222. Min Act: -0.0002

Data Index: 573783 (C4 (Web Text))

Max Activating Token Index: 548

Text #6

Max Range: 1.1452. Min Range: -1.1452

Max Act: 1.0342. Min Act: -0.0002

Data Index: 1119544 (C4 (Web Text))

Max Activating Token Index: 577

Text #7

Max Range: 1.1452. Min Range: -1.1452

Max Act: 0.9111. Min Act: -0.0002

Data Index: 435821 (C4 (Web Text))

Max Activating Token Index: 616

Text #8

Max Range: 1.1452. Min Range: -1.1452

Max Act: 0.8747. Min Act: -0.0002

Data Index: 546098 (C4 (Web Text))

Max Activating Token Index: 229

Text #9

Max Range: 1.1452. Min Range: -1.1452

Max Act: 0.9176. Min Act: -0.0002

Data Index: 573987 (C4 (Web Text))

Max Activating Token Index: 931

Text #10

Max Range: 1.1452. Min Range: -1.1452

Max Act: 0.9947. Min Act: -0.0002

Data Index: 285189 (C4 (Web Text))

Max Activating Token Index: 907

Text #11

Max Range: 1.1452. Min Range: -1.1452

Max Act: 0.9375. Min Act: -0.0002

Data Index: 514113 (C4 (Web Text))

Max Activating Token Index: 966

Text #12

Max Range: 1.1452. Min Range: -1.1452

Max Act: 0.9569. Min Act: -0.0002

Data Index: 853493 (C4 (Web Text))

Max Activating Token Index: 87

Text #13

Max Range: 1.1452. Min Range: -1.1452

Max Act: 0.9026. Min Act: -0.0002

Data Index: 177833 (C4 (Web Text))

Max Activating Token Index: 107

Text #14

Max Range: 1.1452. Min Range: -1.1452

Max Act: 0.8728. Min Act: -0.0002

Data Index: 381687 (C4 (Web Text))

Max Activating Token Index: 287

Text #15

Max Range: 1.1452. Min Range: -1.1452

Max Act: 0.8626. Min Act: -0.0002

Data Index: 1123169 (C4 (Web Text))

Max Activating Token Index: 780

Text #16

Max Range: 1.1452. Min Range: -1.1452

Max Act: 0.9070. Min Act: -0.0002

Data Index: 447555 (C4 (Web Text))

Max Activating Token Index: 688

Text #17

Max Range: 1.1452. Min Range: -1.1452

Max Act: 0.9305. Min Act: -0.0002

Data Index: 5485 (C4 (Web Text))

Max Activating Token Index: 662

Text #18

Max Range: 1.1452. Min Range: -1.1452

Max Act: 0.8406. Min Act: -0.0002

Data Index: 957736 (C4 (Web Text))

Max Activating Token Index: 731

Text #19

Max Range: 1.1452. Min Range: -1.1452

Max Act: 0.8975. Min Act: -0.0002

Data Index: 793388 (C4 (Web Text))

Max Activating Token Index: 949