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

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

Neuron 2826 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5981. Min Range: -1.5981

Max Act: 1.4819. Min Act: -0.0000

Data Index: 1284801 (C4 (Web Text))

Max Activating Token Index: 774

Text #1

Max Range: 1.5981. Min Range: -1.5981

Max Act: 1.5981. Min Act: -0.0000

Data Index: 1356339 (C4 (Web Text))

Max Activating Token Index: 896

Text #2

Max Range: 1.5981. Min Range: -1.5981

Max Act: 1.4583. Min Act: -0.0000

Data Index: 307268 (C4 (Web Text))

Max Activating Token Index: 455

Text #3

Max Range: 1.5981. Min Range: -1.5981

Max Act: 1.4488. Min Act: -0.0000

Data Index: 854333 (C4 (Web Text))

Max Activating Token Index: 403

Text #4

Max Range: 1.5981. Min Range: -1.5981

Max Act: 1.3379. Min Act: -0.0000

Data Index: 1015747 (C4 (Web Text))

Max Activating Token Index: 126

Text #5

Max Range: 1.5981. Min Range: -1.5981

Max Act: 1.3590. Min Act: -0.0000

Data Index: 1162653 (C4 (Web Text))

Max Activating Token Index: 389

Text #6

Max Range: 1.5981. Min Range: -1.5981

Max Act: 1.3208. Min Act: -0.0000

Data Index: 703995 (C4 (Web Text))

Max Activating Token Index: 72

Text #7

Max Range: 1.5981. Min Range: -1.5981

Max Act: 1.3377. Min Act: -0.0000

Data Index: 764058 (C4 (Web Text))

Max Activating Token Index: 565

Text #8

Max Range: 1.5981. Min Range: -1.5981

Max Act: 1.3292. Min Act: -0.0000

Data Index: 260646 (C4 (Web Text))

Max Activating Token Index: 943

Text #9

Max Range: 1.5981. Min Range: -1.5981

Max Act: 1.3171. Min Act: -0.0000

Data Index: 1012907 (C4 (Web Text))

Max Activating Token Index: 485

Text #10

Max Range: 1.5981. Min Range: -1.5981

Max Act: 1.3466. Min Act: -0.0000

Data Index: 1177634 (C4 (Web Text))

Max Activating Token Index: 451

Text #11

Max Range: 1.5981. Min Range: -1.5981

Max Act: 1.3081. Min Act: -0.0000

Data Index: 91829 (C4 (Web Text))

Max Activating Token Index: 582

Text #12

Max Range: 1.5981. Min Range: -1.5981

Max Act: 1.3115. Min Act: -0.0000

Data Index: 467976 (C4 (Web Text))

Max Activating Token Index: 667

Text #13

Max Range: 1.5981. Min Range: -1.5981

Max Act: 1.2061. Min Act: -0.0000

Data Index: 396970 (C4 (Web Text))

Max Activating Token Index: 182

Text #14

Max Range: 1.5981. Min Range: -1.5981

Max Act: 1.3576. Min Act: -0.0000

Data Index: 1356222 (C4 (Web Text))

Max Activating Token Index: 696

Text #15

Max Range: 1.5981. Min Range: -1.5981

Max Act: 1.2761. Min Act: -0.0000

Data Index: 1256837 (C4 (Web Text))

Max Activating Token Index: 802

Text #16

Max Range: 1.5981. Min Range: -1.5981

Max Act: 1.2242. Min Act: -0.0000

Data Index: 456972 (C4 (Web Text))

Max Activating Token Index: 871

Text #17

Max Range: 1.5981. Min Range: -1.5981

Max Act: 1.1582. Min Act: -0.0000

Data Index: 393710 (C4 (Web Text))

Max Activating Token Index: 125

Text #18

Max Range: 1.5981. Min Range: -1.5981

Max Act: 1.2659. Min Act: -0.0000

Data Index: 861403 (C4 (Web Text))

Max Activating Token Index: 593

Text #19

Max Range: 1.5981. Min Range: -1.5981

Max Act: 1.2646. Min Act: -0.0000

Data Index: 581127 (C4 (Web Text))

Max Activating Token Index: 832