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

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

Neuron 4739 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7249. Min Range: -0.7249

Max Act: 0.7249. Min Act: -0.0000

Data Index: 412946 (C4 (Web Text))

Max Activating Token Index: 251

Text #1

Max Range: 0.7249. Min Range: -0.7249

Max Act: 0.6385. Min Act: -0.0000

Data Index: 42359 (C4 (Web Text))

Max Activating Token Index: 665

Text #2

Max Range: 0.7249. Min Range: -0.7249

Max Act: 0.6324. Min Act: -0.0000

Data Index: 918805 (C4 (Web Text))

Max Activating Token Index: 259

Text #3

Max Range: 0.7249. Min Range: -0.7249

Max Act: 0.5976. Min Act: -0.0000

Data Index: 599711 (C4 (Web Text))

Max Activating Token Index: 471

Text #4

Max Range: 0.7249. Min Range: -0.7249

Max Act: 0.5900. Min Act: 0.0000

Data Index: 1293896 (C4 (Web Text))

Max Activating Token Index: 1001

Text #5

Max Range: 0.7249. Min Range: -0.7249

Max Act: 0.5480. Min Act: -0.0000

Data Index: 18027 (C4 (Web Text))

Max Activating Token Index: 124

Text #6

Max Range: 0.7249. Min Range: -0.7249

Max Act: 0.5484. Min Act: 0.0000

Data Index: 1320164 (C4 (Web Text))

Max Activating Token Index: 928

Text #7

Max Range: 0.7249. Min Range: -0.7249

Max Act: 0.5189. Min Act: -0.0000

Data Index: 784695 (C4 (Web Text))

Max Activating Token Index: 169

Text #8

Max Range: 0.7249. Min Range: -0.7249

Max Act: 0.5217. Min Act: -0.0000

Data Index: 206218 (C4 (Web Text))

Max Activating Token Index: 703

Text #9

Max Range: 0.7249. Min Range: -0.7249

Max Act: 0.5043. Min Act: -0.0000

Data Index: 554060 (C4 (Web Text))

Max Activating Token Index: 145

Text #10

Max Range: 0.7249. Min Range: -0.7249

Max Act: 0.5441. Min Act: -0.0000

Data Index: 824860 (C4 (Web Text))

Max Activating Token Index: 161

Text #11

Max Range: 0.7249. Min Range: -0.7249

Max Act: 0.5047. Min Act: -0.0000

Data Index: 98403 (C4 (Web Text))

Max Activating Token Index: 503

Text #12

Max Range: 0.7249. Min Range: -0.7249

Max Act: 0.4763. Min Act: -0.0000

Data Index: 910672 (C4 (Web Text))

Max Activating Token Index: 730

Text #13

Max Range: 0.7249. Min Range: -0.7249

Max Act: 0.4459. Min Act: -0.0000

Data Index: 456335 (C4 (Web Text))

Max Activating Token Index: 119

Text #14

Max Range: 0.7249. Min Range: -0.7249

Max Act: 0.4537. Min Act: -0.0000

Data Index: 535217 (C4 (Web Text))

Max Activating Token Index: 832

Text #15

Max Range: 0.7249. Min Range: -0.7249

Max Act: 0.4442. Min Act: 0.0000

Data Index: 1143022 (C4 (Web Text))

Max Activating Token Index: 50

Text #16

Max Range: 0.7249. Min Range: -0.7249

Max Act: 0.4427. Min Act: -0.0000

Data Index: 711134 (C4 (Web Text))

Max Activating Token Index: 578

Text #17

Max Range: 0.7249. Min Range: -0.7249

Max Act: 0.4133. Min Act: -0.0000

Data Index: 599834 (C4 (Web Text))

Max Activating Token Index: 558

Text #18

Max Range: 0.7249. Min Range: -0.7249

Max Act: 0.4368. Min Act: -0.0000

Data Index: 877142 (C4 (Web Text))

Max Activating Token Index: 548

Text #19

Max Range: 0.7249. Min Range: -0.7249

Max Act: 0.4277. Min Act: -0.0000

Data Index: 285453 (C4 (Web Text))

Max Activating Token Index: 198