Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 613 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.8095. Min Range: -0.8095

Max Act: 0.7574. Min Act: -0.0001

Data Index: 405044 (C4 (Web Text))

Max Activating Token Index: 872

Text #1

Max Range: 0.8095. Min Range: -0.8095

Max Act: 0.8095. Min Act: -0.0001

Data Index: 396406 (C4 (Web Text))

Max Activating Token Index: 942

Text #2

Max Range: 0.8095. Min Range: -0.8095

Max Act: 0.7138. Min Act: -0.0001

Data Index: 1234674 (C4 (Web Text))

Max Activating Token Index: 339

Text #3

Max Range: 0.8095. Min Range: -0.8095

Max Act: 0.6758. Min Act: -0.0001

Data Index: 141569 (C4 (Web Text))

Max Activating Token Index: 116

Text #4

Max Range: 0.8095. Min Range: -0.8095

Max Act: 0.6639. Min Act: -0.0001

Data Index: 123066 (C4 (Web Text))

Max Activating Token Index: 51

Text #5

Max Range: 0.8095. Min Range: -0.8095

Max Act: 0.6383. Min Act: -0.0001

Data Index: 211958 (C4 (Web Text))

Max Activating Token Index: 822

Text #6

Max Range: 0.8095. Min Range: -0.8095

Max Act: 0.6385. Min Act: -0.0001

Data Index: 172618 (C4 (Web Text))

Max Activating Token Index: 134

Text #7

Max Range: 0.8095. Min Range: -0.8095

Max Act: 0.5555. Min Act: -0.0001

Data Index: 1236856 (C4 (Web Text))

Max Activating Token Index: 701

Text #8

Max Range: 0.8095. Min Range: -0.8095

Max Act: 0.5911. Min Act: -0.0001

Data Index: 733958 (C4 (Web Text))

Max Activating Token Index: 980

Text #9

Max Range: 0.8095. Min Range: -0.8095

Max Act: 0.6215. Min Act: -0.0001

Data Index: 269867 (C4 (Web Text))

Max Activating Token Index: 302

Text #10

Max Range: 0.8095. Min Range: -0.8095

Max Act: 0.5986. Min Act: -0.0001

Data Index: 306047 (C4 (Web Text))

Max Activating Token Index: 96

Text #11

Max Range: 0.8095. Min Range: -0.8095

Max Act: 0.5950. Min Act: -0.0001

Data Index: 1207666 (C4 (Web Text))

Max Activating Token Index: 689

Text #12

Max Range: 0.8095. Min Range: -0.8095

Max Act: 0.6135. Min Act: -0.0001

Data Index: 679548 (C4 (Web Text))

Max Activating Token Index: 18

Text #13

Max Range: 0.8095. Min Range: -0.8095

Max Act: 0.6055. Min Act: -0.0001

Data Index: 108298 (C4 (Web Text))

Max Activating Token Index: 115

Text #14

Max Range: 0.8095. Min Range: -0.8095

Max Act: 0.6333. Min Act: -0.0001

Data Index: 1274783 (C4 (Web Text))

Max Activating Token Index: 223

Text #15

Max Range: 0.8095. Min Range: -0.8095

Max Act: 0.5848. Min Act: -0.0001

Data Index: 1169225 (C4 (Web Text))

Max Activating Token Index: 552

Text #16

Max Range: 0.8095. Min Range: -0.8095

Max Act: 0.5824. Min Act: -0.0001

Data Index: 732183 (C4 (Web Text))

Max Activating Token Index: 606

Text #17

Max Range: 0.8095. Min Range: -0.8095

Max Act: 0.5891. Min Act: -0.0001

Data Index: 38726 (C4 (Web Text))

Max Activating Token Index: 489

Text #18

Max Range: 0.8095. Min Range: -0.8095

Max Act: 0.5743. Min Act: -0.0001

Data Index: 1250956 (C4 (Web Text))

Max Activating Token Index: 82

Text #19

Max Range: 0.8095. Min Range: -0.8095

Max Act: 0.5576. Min Act: -0.0001

Data Index: 743417 (C4 (Web Text))

Max Activating Token Index: 384