Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1851 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.4059. Min Range: -0.4059

Max Act: 0.4059. Min Act: -0.0001

Data Index: 1076990 (C4 (Web Text))

Max Activating Token Index: 82

Text #1

Max Range: 0.4059. Min Range: -0.4059

Max Act: 0.3989. Min Act: -0.0001

Data Index: 502106 (C4 (Web Text))

Max Activating Token Index: 150

Text #2

Max Range: 0.4059. Min Range: -0.4059

Max Act: 0.3947. Min Act: -0.0001

Data Index: 407434 (C4 (Web Text))

Max Activating Token Index: 116

Text #3

Max Range: 0.4059. Min Range: -0.4059

Max Act: 0.3881. Min Act: -0.0001

Data Index: 266822 (C4 (Web Text))

Max Activating Token Index: 727

Text #4

Max Range: 0.4059. Min Range: -0.4059

Max Act: 0.3985. Min Act: -0.0001

Data Index: 379516 (C4 (Web Text))

Max Activating Token Index: 137

Text #5

Max Range: 0.4059. Min Range: -0.4059

Max Act: 0.3619. Min Act: -0.0001

Data Index: 95128 (C4 (Web Text))

Max Activating Token Index: 630

Text #6

Max Range: 0.4059. Min Range: -0.4059

Max Act: 0.3724. Min Act: -0.0001

Data Index: 1281234 (C4 (Web Text))

Max Activating Token Index: 87

Text #7

Max Range: 0.4059. Min Range: -0.4059

Max Act: 0.3774. Min Act: -0.0001

Data Index: 144222 (C4 (Web Text))

Max Activating Token Index: 707

Text #8

Max Range: 0.4059. Min Range: -0.4059

Max Act: 0.3542. Min Act: -0.0001

Data Index: 1246925 (C4 (Web Text))

Max Activating Token Index: 676

Text #9

Max Range: 0.4059. Min Range: -0.4059

Max Act: 0.3765. Min Act: -0.0001

Data Index: 628167 (C4 (Web Text))

Max Activating Token Index: 109

Text #10

Max Range: 0.4059. Min Range: -0.4059

Max Act: 0.3622. Min Act: -0.0001

Data Index: 13763 (C4 (Web Text))

Max Activating Token Index: 777

Text #11

Max Range: 0.4059. Min Range: -0.4059

Max Act: 0.3601. Min Act: -0.0001

Data Index: 746905 (C4 (Web Text))

Max Activating Token Index: 987

Text #12

Max Range: 0.4059. Min Range: -0.4059

Max Act: 0.3593. Min Act: -0.0001

Data Index: 992584 (C4 (Web Text))

Max Activating Token Index: 323

Text #13

Max Range: 0.4059. Min Range: -0.4059

Max Act: 0.3541. Min Act: -0.0001

Data Index: 437013 (C4 (Web Text))

Max Activating Token Index: 112

Text #14

Max Range: 0.4059. Min Range: -0.4059

Max Act: 0.3573. Min Act: -0.0001

Data Index: 1197068 (C4 (Web Text))

Max Activating Token Index: 867

Text #15

Max Range: 0.4059. Min Range: -0.4059

Max Act: 0.3560. Min Act: -0.0001

Data Index: 1348417 (C4 (Web Text))

Max Activating Token Index: 570

Text #16

Max Range: 0.4059. Min Range: -0.4059

Max Act: 0.3745. Min Act: -0.0001

Data Index: 512638 (C4 (Web Text))

Max Activating Token Index: 587

Text #17

Max Range: 0.4059. Min Range: -0.4059

Max Act: 0.3468. Min Act: -0.0001

Data Index: 510344 (C4 (Web Text))

Max Activating Token Index: 382

Text #18

Max Range: 0.4059. Min Range: -0.4059

Max Act: 0.3425. Min Act: -0.0001

Data Index: 215322 (C4 (Web Text))

Max Activating Token Index: 870

Text #19

Max Range: 0.4059. Min Range: -0.4059

Max Act: 0.3524. Min Act: -0.0001

Data Index: 445306 (C4 (Web Text))

Max Activating Token Index: 57