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

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

Neuron 3052 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7653. Min Range: -0.7653

Max Act: 0.7653. Min Act: -0.0001

Data Index: 306047 (C4 (Web Text))

Max Activating Token Index: 147

Text #1

Max Range: 0.7653. Min Range: -0.7653

Max Act: 0.7087. Min Act: -0.0000

Data Index: 786389 (C4 (Web Text))

Max Activating Token Index: 105

Text #2

Max Range: 0.7653. Min Range: -0.7653

Max Act: 0.6246. Min Act: -0.0000

Data Index: 415653 (C4 (Web Text))

Max Activating Token Index: 258

Text #3

Max Range: 0.7653. Min Range: -0.7653

Max Act: 0.6279. Min Act: -0.0000

Data Index: 961536 (C4 (Web Text))

Max Activating Token Index: 914

Text #4

Max Range: 0.7653. Min Range: -0.7653

Max Act: 0.6246. Min Act: 0.0000

Data Index: 358198 (C4 (Web Text))

Max Activating Token Index: 36

Text #5

Max Range: 0.7653. Min Range: -0.7653

Max Act: 0.6085. Min Act: -0.0000

Data Index: 1116289 (C4 (Web Text))

Max Activating Token Index: 45

Text #6

Max Range: 0.7653. Min Range: -0.7653

Max Act: 0.5849. Min Act: -0.0000

Data Index: 1114247 (C4 (Web Text))

Max Activating Token Index: 238

Text #7

Max Range: 0.7653. Min Range: -0.7653

Max Act: 0.6207. Min Act: -0.0000

Data Index: 35917 (C4 (Web Text))

Max Activating Token Index: 741

Text #8

Max Range: 0.7653. Min Range: -0.7653

Max Act: 0.5953. Min Act: -0.0000

Data Index: 813025 (C4 (Web Text))

Max Activating Token Index: 701

Text #9

Max Range: 0.7653. Min Range: -0.7653

Max Act: 0.5901. Min Act: -0.0000

Data Index: 15275 (C4 (Web Text))

Max Activating Token Index: 210

Text #10

Max Range: 0.7653. Min Range: -0.7653

Max Act: 0.6056. Min Act: -0.0001

Data Index: 310917 (C4 (Web Text))

Max Activating Token Index: 20

Text #11

Max Range: 0.7653. Min Range: -0.7653

Max Act: 0.5834. Min Act: -0.0000

Data Index: 663088 (C4 (Web Text))

Max Activating Token Index: 922

Text #12

Max Range: 0.7653. Min Range: -0.7653

Max Act: 0.5550. Min Act: -0.0000

Data Index: 658753 (C4 (Web Text))

Max Activating Token Index: 830

Text #13

Max Range: 0.7653. Min Range: -0.7653

Max Act: 0.5539. Min Act: -0.0000

Data Index: 549087 (C4 (Web Text))

Max Activating Token Index: 233

Text #14

Max Range: 0.7653. Min Range: -0.7653

Max Act: 0.5687. Min Act: -0.0000

Data Index: 1242966 (C4 (Web Text))

Max Activating Token Index: 792

Text #15

Max Range: 0.7653. Min Range: -0.7653

Max Act: 0.6011. Min Act: -0.0000

Data Index: 619089 (C4 (Web Text))

Max Activating Token Index: 983

Text #16

Max Range: 0.7653. Min Range: -0.7653

Max Act: 0.5627. Min Act: -0.0000

Data Index: 1238726 (C4 (Web Text))

Max Activating Token Index: 348

Text #17

Max Range: 0.7653. Min Range: -0.7653

Max Act: 0.5379. Min Act: -0.0000

Data Index: 519953 (C4 (Web Text))

Max Activating Token Index: 417

Text #18

Max Range: 0.7653. Min Range: -0.7653

Max Act: 0.5311. Min Act: -0.0000

Data Index: 803768 (C4 (Web Text))

Max Activating Token Index: 515

Text #19

Max Range: 0.7653. Min Range: -0.7653

Max Act: 0.5097. Min Act: -0.0000

Data Index: 585173 (C4 (Web Text))

Max Activating Token Index: 488