Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3734 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.8050. Min Range: -1.8050

Max Act: 1.7692. Min Act: -0.0001

Data Index: 364826 (C4 (Web Text))

Max Activating Token Index: 275

Text #1

Max Range: 1.8050. Min Range: -1.8050

Max Act: 1.7646. Min Act: -0.0001

Data Index: 648049 (C4 (Web Text))

Max Activating Token Index: 301

Text #2

Max Range: 1.8050. Min Range: -1.8050

Max Act: 1.7586. Min Act: -0.0000

Data Index: 1076600 (C4 (Web Text))

Max Activating Token Index: 344

Text #3

Max Range: 1.8050. Min Range: -1.8050

Max Act: 1.7473. Min Act: -0.0001

Data Index: 1150924 (C4 (Web Text))

Max Activating Token Index: 448

Text #4

Max Range: 1.8050. Min Range: -1.8050

Max Act: 1.8050. Min Act: -0.0001

Data Index: 1041452 (C4 (Web Text))

Max Activating Token Index: 367

Text #5

Max Range: 1.8050. Min Range: -1.8050

Max Act: 1.7129. Min Act: -0.0000

Data Index: 333371 (C4 (Web Text))

Max Activating Token Index: 162

Text #6

Max Range: 1.8050. Min Range: -1.8050

Max Act: 1.7219. Min Act: -0.0001

Data Index: 195667 (C4 (Web Text))

Max Activating Token Index: 276

Text #7

Max Range: 1.8050. Min Range: -1.8050

Max Act: 1.5994. Min Act: -0.0001

Data Index: 253849 (C4 (Web Text))

Max Activating Token Index: 692

Text #8

Max Range: 1.8050. Min Range: -1.8050

Max Act: 1.5732. Min Act: -0.0000

Data Index: 114287 (C4 (Web Text))

Max Activating Token Index: 13

Text #9

Max Range: 1.8050. Min Range: -1.8050

Max Act: 1.6134. Min Act: -0.0001

Data Index: 637730 (C4 (Web Text))

Max Activating Token Index: 755

Text #10

Max Range: 1.8050. Min Range: -1.8050

Max Act: 1.5309. Min Act: -0.0000

Data Index: 665581 (C4 (Web Text))

Max Activating Token Index: 238

Text #11

Max Range: 1.8050. Min Range: -1.8050

Max Act: 1.5310. Min Act: -0.0001

Data Index: 52306 (C4 (Web Text))

Max Activating Token Index: 564

Text #12

Max Range: 1.8050. Min Range: -1.8050

Max Act: 1.4144. Min Act: -0.0001

Data Index: 191147 (C4 (Web Text))

Max Activating Token Index: 703

Text #13

Max Range: 1.8050. Min Range: -1.8050

Max Act: 1.4007. Min Act: -0.0000

Data Index: 100075 (C4 (Web Text))

Max Activating Token Index: 474

Text #14

Max Range: 1.8050. Min Range: -1.8050

Max Act: 1.3699. Min Act: -0.0001

Data Index: 840939 (C4 (Web Text))

Max Activating Token Index: 383

Text #15

Max Range: 1.8050. Min Range: -1.8050

Max Act: 1.5034. Min Act: -0.0001

Data Index: 857660 (C4 (Web Text))

Max Activating Token Index: 1001

Text #16

Max Range: 1.8050. Min Range: -1.8050

Max Act: 1.4113. Min Act: -0.0001

Data Index: 10426 (C4 (Web Text))

Max Activating Token Index: 246

Text #17

Max Range: 1.8050. Min Range: -1.8050

Max Act: 1.3380. Min Act: -0.0000

Data Index: 189378 (C4 (Web Text))

Max Activating Token Index: 378

Text #18

Max Range: 1.8050. Min Range: -1.8050

Max Act: 1.3864. Min Act: -0.0001

Data Index: 1189362 (C4 (Web Text))

Max Activating Token Index: 771

Text #19

Max Range: 1.8050. Min Range: -1.8050

Max Act: 1.3456. Min Act: -0.0001

Data Index: 168593 (C4 (Web Text))

Max Activating Token Index: 615