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

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

Neuron 3246 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7588. Min Range: -0.7588

Max Act: 0.7588. Min Act: -0.0000

Data Index: 629920 (C4 (Web Text))

Max Activating Token Index: 975

Text #1

Max Range: 0.7588. Min Range: -0.7588

Max Act: 0.7134. Min Act: -0.0000

Data Index: 605231 (C4 (Web Text))

Max Activating Token Index: 355

Text #2

Max Range: 0.7588. Min Range: -0.7588

Max Act: 0.6586. Min Act: -0.0000

Data Index: 1224765 (C4 (Web Text))

Max Activating Token Index: 607

Text #3

Max Range: 0.7588. Min Range: -0.7588

Max Act: 0.6072. Min Act: -0.0000

Data Index: 829916 (C4 (Web Text))

Max Activating Token Index: 533

Text #4

Max Range: 0.7588. Min Range: -0.7588

Max Act: 0.5736. Min Act: -0.0000

Data Index: 1007368 (C4 (Web Text))

Max Activating Token Index: 885

Text #5

Max Range: 0.7588. Min Range: -0.7588

Max Act: 0.6004. Min Act: -0.0001

Data Index: 863016 (C4 (Web Text))

Max Activating Token Index: 293

Text #6

Max Range: 0.7588. Min Range: -0.7588

Max Act: 0.5398. Min Act: -0.0000

Data Index: 959036 (C4 (Web Text))

Max Activating Token Index: 1011

Text #7

Max Range: 0.7588. Min Range: -0.7588

Max Act: 0.5071. Min Act: -0.0000

Data Index: 875607 (C4 (Web Text))

Max Activating Token Index: 167

Text #8

Max Range: 0.7588. Min Range: -0.7588

Max Act: 0.5505. Min Act: -0.0000

Data Index: 68838 (C4 (Web Text))

Max Activating Token Index: 77

Text #9

Max Range: 0.7588. Min Range: -0.7588

Max Act: 0.5833. Min Act: -0.0000

Data Index: 1104833 (C4 (Web Text))

Max Activating Token Index: 223

Text #10

Max Range: 0.7588. Min Range: -0.7588

Max Act: 0.5994. Min Act: -0.0000

Data Index: 1256242 (C4 (Web Text))

Max Activating Token Index: 544

Text #11

Max Range: 0.7588. Min Range: -0.7588

Max Act: 0.5353. Min Act: -0.0000

Data Index: 1129451 (C4 (Web Text))

Max Activating Token Index: 656

Text #12

Max Range: 0.7588. Min Range: -0.7588

Max Act: 0.5465. Min Act: -0.0000

Data Index: 1040850 (C4 (Web Text))

Max Activating Token Index: 131

Text #13

Max Range: 0.7588. Min Range: -0.7588

Max Act: 0.5489. Min Act: -0.0000

Data Index: 1031428 (C4 (Web Text))

Max Activating Token Index: 411

Text #14

Max Range: 0.7588. Min Range: -0.7588

Max Act: 0.5329. Min Act: -0.0000

Data Index: 372104 (C4 (Web Text))

Max Activating Token Index: 215

Text #15

Max Range: 0.7588. Min Range: -0.7588

Max Act: 0.4922. Min Act: -0.0000

Data Index: 379461 (C4 (Web Text))

Max Activating Token Index: 834

Text #16

Max Range: 0.7588. Min Range: -0.7588

Max Act: 0.5461. Min Act: -0.0000

Data Index: 274876 (C4 (Web Text))

Max Activating Token Index: 965

Text #17

Max Range: 0.7588. Min Range: -0.7588

Max Act: 0.5460. Min Act: -0.0000

Data Index: 469084 (C4 (Web Text))

Max Activating Token Index: 272

Text #18

Max Range: 0.7588. Min Range: -0.7588

Max Act: 0.5290. Min Act: -0.0000

Data Index: 1327941 (C4 (Web Text))

Max Activating Token Index: 237

Text #19

Max Range: 0.7588. Min Range: -0.7588

Max Act: 0.4995. Min Act: -0.0000

Data Index: 530136 (C4 (Web Text))

Max Activating Token Index: 648