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

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

Neuron 1448 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5986. Min Range: -0.5986

Max Act: 0.5986. Min Act: -0.0000

Data Index: 273686 (C4 (Web Text))

Max Activating Token Index: 829

Text #1

Max Range: 0.5986. Min Range: -0.5986

Max Act: 0.5305. Min Act: -0.0000

Data Index: 891526 (C4 (Web Text))

Max Activating Token Index: 555

Text #2

Max Range: 0.5986. Min Range: -0.5986

Max Act: 0.4138. Min Act: -0.0000

Data Index: 511513 (C4 (Web Text))

Max Activating Token Index: 223

Text #3

Max Range: 0.5986. Min Range: -0.5986

Max Act: 0.4397. Min Act: -0.0000

Data Index: 297287 (C4 (Web Text))

Max Activating Token Index: 199

Text #4

Max Range: 0.5986. Min Range: -0.5986

Max Act: 0.4423. Min Act: -0.0000

Data Index: 928164 (C4 (Web Text))

Max Activating Token Index: 655

Text #5

Max Range: 0.5986. Min Range: -0.5986

Max Act: 0.4370. Min Act: -0.0000

Data Index: 1082612 (C4 (Web Text))

Max Activating Token Index: 174

Text #6

Max Range: 0.5986. Min Range: -0.5986

Max Act: 0.4181. Min Act: -0.0000

Data Index: 1315714 (C4 (Web Text))

Max Activating Token Index: 528

Text #7

Max Range: 0.5986. Min Range: -0.5986

Max Act: 0.4192. Min Act: -0.0000

Data Index: 662386 (C4 (Web Text))

Max Activating Token Index: 292

Text #8

Max Range: 0.5986. Min Range: -0.5986

Max Act: 0.3967. Min Act: -0.0000

Data Index: 100689 (C4 (Web Text))

Max Activating Token Index: 259

Text #9

Max Range: 0.5986. Min Range: -0.5986

Max Act: 0.4042. Min Act: -0.0000

Data Index: 853948 (C4 (Web Text))

Max Activating Token Index: 584

Text #10

Max Range: 0.5986. Min Range: -0.5986

Max Act: 0.4031. Min Act: -0.0000

Data Index: 1042631 (C4 (Web Text))

Max Activating Token Index: 36

Text #11

Max Range: 0.5986. Min Range: -0.5986

Max Act: 0.3817. Min Act: -0.0000

Data Index: 1095147 (C4 (Web Text))

Max Activating Token Index: 804

Text #12

Max Range: 0.5986. Min Range: -0.5986

Max Act: 0.3915. Min Act: -0.0000

Data Index: 866749 (C4 (Web Text))

Max Activating Token Index: 437

Text #13

Max Range: 0.5986. Min Range: -0.5986

Max Act: 0.3892. Min Act: -0.0000

Data Index: 180711 (C4 (Web Text))

Max Activating Token Index: 793

Text #14

Max Range: 0.5986. Min Range: -0.5986

Max Act: 0.3845. Min Act: -0.0000

Data Index: 751129 (C4 (Web Text))

Max Activating Token Index: 1005

Text #15

Max Range: 0.5986. Min Range: -0.5986

Max Act: 0.3945. Min Act: -0.0000

Data Index: 656676 (C4 (Web Text))

Max Activating Token Index: 1011

Text #16

Max Range: 0.5986. Min Range: -0.5986

Max Act: 0.3667. Min Act: -0.0000

Data Index: 639953 (C4 (Web Text))

Max Activating Token Index: 427

Text #17

Max Range: 0.5986. Min Range: -0.5986

Max Act: 0.3767. Min Act: -0.0000

Data Index: 331809 (C4 (Web Text))

Max Activating Token Index: 264

Text #18

Max Range: 0.5986. Min Range: -0.5986

Max Act: 0.3540. Min Act: -0.0000

Data Index: 664631 (C4 (Web Text))

Max Activating Token Index: 572

Text #19

Max Range: 0.5986. Min Range: -0.5986

Max Act: 0.3519. Min Act: -0.0000

Data Index: 1092805 (C4 (Web Text))

Max Activating Token Index: 646