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

Dataset: The Pile

Neuron 3783 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.4037. Min Range: -5.4037

Max Act: 5.4037. Min Act: -0.0000

Data Index: 1831435 (The Pile)

Max Activating Token Index: 554

Text #1

Max Range: 5.4037. Min Range: -5.4037

Max Act: 5.1250. Min Act: -0.0000

Data Index: 1017371 (The Pile)

Max Activating Token Index: 521

Text #2

Max Range: 5.4037. Min Range: -5.4037

Max Act: 5.2984. Min Act: -0.0000

Data Index: 1522375 (The Pile)

Max Activating Token Index: 629

Text #3

Max Range: 5.4037. Min Range: -5.4037

Max Act: 4.8566. Min Act: -0.0000

Data Index: 211101 (The Pile)

Max Activating Token Index: 137

Text #4

Max Range: 5.4037. Min Range: -5.4037

Max Act: 4.6515. Min Act: -0.0000

Data Index: 2539 (The Pile)

Max Activating Token Index: 504

Text #5

Max Range: 5.4037. Min Range: -5.4037

Max Act: 5.1165. Min Act: -0.0000

Data Index: 696973 (The Pile)

Max Activating Token Index: 176

Text #6

Max Range: 5.4037. Min Range: -5.4037

Max Act: 4.7201. Min Act: -0.0000

Data Index: 1148457 (The Pile)

Max Activating Token Index: 434

Text #7

Max Range: 5.4037. Min Range: -5.4037

Max Act: 4.2414. Min Act: -0.0000

Data Index: 1331153 (The Pile)

Max Activating Token Index: 530

Text #8

Max Range: 5.4037. Min Range: -5.4037

Max Act: 4.5393. Min Act: -0.0000

Data Index: 1264041 (The Pile)

Max Activating Token Index: 473

Text #9

Max Range: 5.4037. Min Range: -5.4037

Max Act: 4.7370. Min Act: -0.0000

Data Index: 1304712 (The Pile)

Max Activating Token Index: 732

Text #10

Max Range: 5.4037. Min Range: -5.4037

Max Act: 4.6180. Min Act: -0.0000

Data Index: 1937886 (The Pile)

Max Activating Token Index: 241

Text #11

Max Range: 5.4037. Min Range: -5.4037

Max Act: 4.7120. Min Act: -0.0000

Data Index: 20321 (The Pile)

Max Activating Token Index: 587

Text #12

Max Range: 5.4037. Min Range: -5.4037

Max Act: 4.4340. Min Act: -0.0000

Data Index: 230432 (The Pile)

Max Activating Token Index: 162

Text #13

Max Range: 5.4037. Min Range: -5.4037

Max Act: 4.9052. Min Act: -0.0000

Data Index: 605512 (The Pile)

Max Activating Token Index: 449

Text #14

Max Range: 5.4037. Min Range: -5.4037

Max Act: 4.5065. Min Act: -0.0000

Data Index: 1380157 (The Pile)

Max Activating Token Index: 452

Text #15

Max Range: 5.4037. Min Range: -5.4037

Max Act: 4.8479. Min Act: -0.0000

Data Index: 332417 (The Pile)

Max Activating Token Index: 291

Text #16

Max Range: 5.4037. Min Range: -5.4037

Max Act: 4.5266. Min Act: -0.0001

Data Index: 1558027 (The Pile)

Max Activating Token Index: 533

Text #17

Max Range: 5.4037. Min Range: -5.4037

Max Act: 4.4998. Min Act: -0.0000

Data Index: 1913472 (The Pile)

Max Activating Token Index: 697

Text #18

Max Range: 5.4037. Min Range: -5.4037

Max Act: 4.3918. Min Act: -0.0000

Data Index: 489172 (The Pile)

Max Activating Token Index: 559

Text #19

Max Range: 5.4037. Min Range: -5.4037

Max Act: 4.3114. Min Act: -0.0000

Data Index: 259288 (The Pile)

Max Activating Token Index: 195