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

Dataset: The Pile

Neuron 4485 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8152. Min Range: -3.8152

Max Act: 3.8152. Min Act: -0.0000

Data Index: 1295794 (The Pile)

Max Activating Token Index: 568

Text #1

Max Range: 3.8152. Min Range: -3.8152

Max Act: 3.5039. Min Act: -0.0000

Data Index: 449244 (The Pile)

Max Activating Token Index: 81

Text #2

Max Range: 3.8152. Min Range: -3.8152

Max Act: 3.3086. Min Act: -0.0000

Data Index: 1541236 (The Pile)

Max Activating Token Index: 169

Text #3

Max Range: 3.8152. Min Range: -3.8152

Max Act: 3.1662. Min Act: -0.0000

Data Index: 154967 (The Pile)

Max Activating Token Index: 307

Text #4

Max Range: 3.8152. Min Range: -3.8152

Max Act: 3.1438. Min Act: -0.0000

Data Index: 903558 (The Pile)

Max Activating Token Index: 372

Text #5

Max Range: 3.8152. Min Range: -3.8152

Max Act: 3.0985. Min Act: -0.0000

Data Index: 184907 (The Pile)

Max Activating Token Index: 501

Text #6

Max Range: 3.8152. Min Range: -3.8152

Max Act: 3.0654. Min Act: -0.0000

Data Index: 237061 (The Pile)

Max Activating Token Index: 601

Text #7

Max Range: 3.8152. Min Range: -3.8152

Max Act: 2.9440. Min Act: -0.0000

Data Index: 1209731 (The Pile)

Max Activating Token Index: 67

Text #8

Max Range: 3.8152. Min Range: -3.8152

Max Act: 3.0709. Min Act: -0.0000

Data Index: 800161 (The Pile)

Max Activating Token Index: 509

Text #9

Max Range: 3.8152. Min Range: -3.8152

Max Act: 2.8129. Min Act: -0.0000

Data Index: 303964 (The Pile)

Max Activating Token Index: 10

Text #10

Max Range: 3.8152. Min Range: -3.8152

Max Act: 2.8111. Min Act: -0.0000

Data Index: 1884114 (The Pile)

Max Activating Token Index: 374

Text #11

Max Range: 3.8152. Min Range: -3.8152

Max Act: 2.8095. Min Act: -0.0000

Data Index: 1265906 (The Pile)

Max Activating Token Index: 410

Text #12

Max Range: 3.8152. Min Range: -3.8152

Max Act: 2.9188. Min Act: -0.0000

Data Index: 253543 (The Pile)

Max Activating Token Index: 459

Text #13

Max Range: 3.8152. Min Range: -3.8152

Max Act: 2.6381. Min Act: -0.0000

Data Index: 1872147 (The Pile)

Max Activating Token Index: 586

Text #14

Max Range: 3.8152. Min Range: -3.8152

Max Act: 2.7506. Min Act: -0.0000

Data Index: 1819692 (The Pile)

Max Activating Token Index: 354

Text #15

Max Range: 3.8152. Min Range: -3.8152

Max Act: 2.6130. Min Act: -0.0000

Data Index: 1403633 (The Pile)

Max Activating Token Index: 467

Text #16

Max Range: 3.8152. Min Range: -3.8152

Max Act: 2.5794. Min Act: -0.0000

Data Index: 1169562 (The Pile)

Max Activating Token Index: 173

Text #17

Max Range: 3.8152. Min Range: -3.8152

Max Act: 2.5624. Min Act: -0.0000

Data Index: 1063398 (The Pile)

Max Activating Token Index: 29

Text #18

Max Range: 3.8152. Min Range: -3.8152

Max Act: 2.6926. Min Act: -0.0000

Data Index: 1241045 (The Pile)

Max Activating Token Index: 815

Text #19

Max Range: 3.8152. Min Range: -3.8152

Max Act: 2.8112. Min Act: -0.0000

Data Index: 776455 (The Pile)

Max Activating Token Index: 389