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

Dataset: The Pile

Neuron 2088 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: 3.6050. Min Range: -3.6050

Max Act: 3.4977. Min Act: -0.0000

Data Index: 855177 (The Pile)

Max Activating Token Index: 47

Text #1

Max Range: 3.6050. Min Range: -3.6050

Max Act: 3.6050. Min Act: -0.0000

Data Index: 216516 (The Pile)

Max Activating Token Index: 475

Text #2

Max Range: 3.6050. Min Range: -3.6050

Max Act: 3.5102. Min Act: -0.0000

Data Index: 1502536 (The Pile)

Max Activating Token Index: 29

Text #3

Max Range: 3.6050. Min Range: -3.6050

Max Act: 3.3302. Min Act: -0.0000

Data Index: 138516 (The Pile)

Max Activating Token Index: 1014

Text #4

Max Range: 3.6050. Min Range: -3.6050

Max Act: 3.2167. Min Act: -0.0000

Data Index: 688168 (The Pile)

Max Activating Token Index: 250

Text #5

Max Range: 3.6050. Min Range: -3.6050

Max Act: 3.3858. Min Act: -0.0000

Data Index: 236641 (The Pile)

Max Activating Token Index: 747

Text #6

Max Range: 3.6050. Min Range: -3.6050

Max Act: 3.4853. Min Act: -0.0000

Data Index: 282955 (The Pile)

Max Activating Token Index: 518

Text #7

Max Range: 3.6050. Min Range: -3.6050

Max Act: 3.3450. Min Act: -0.0000

Data Index: 743062 (The Pile)

Max Activating Token Index: 813

Text #8

Max Range: 3.6050. Min Range: -3.6050

Max Act: 3.1339. Min Act: -0.0000

Data Index: 1914714 (The Pile)

Max Activating Token Index: 29

Text #9

Max Range: 3.6050. Min Range: -3.6050

Max Act: 3.2581. Min Act: -0.0000

Data Index: 1246409 (The Pile)

Max Activating Token Index: 301

Text #10

Max Range: 3.6050. Min Range: -3.6050

Max Act: 3.2260. Min Act: -0.0000

Data Index: 181275 (The Pile)

Max Activating Token Index: 19

Text #11

Max Range: 3.6050. Min Range: -3.6050

Max Act: 3.0808. Min Act: -0.0000

Data Index: 526245 (The Pile)

Max Activating Token Index: 325

Text #12

Max Range: 3.6050. Min Range: -3.6050

Max Act: 3.0258. Min Act: -0.0000

Data Index: 1305421 (The Pile)

Max Activating Token Index: 683

Text #13

Max Range: 3.6050. Min Range: -3.6050

Max Act: 2.6785. Min Act: -0.0000

Data Index: 87366 (The Pile)

Max Activating Token Index: 343

Text #14

Max Range: 3.6050. Min Range: -3.6050

Max Act: 2.5511. Min Act: -0.0000

Data Index: 1844637 (The Pile)

Max Activating Token Index: 102

Text #15

Max Range: 3.6050. Min Range: -3.6050

Max Act: 2.8131. Min Act: -0.0000

Data Index: 706551 (The Pile)

Max Activating Token Index: 129

Text #16

Max Range: 3.6050. Min Range: -3.6050

Max Act: 2.6752. Min Act: -0.0000

Data Index: 1058314 (The Pile)

Max Activating Token Index: 268

Text #17

Max Range: 3.6050. Min Range: -3.6050

Max Act: 2.9281. Min Act: -0.0000

Data Index: 746686 (The Pile)

Max Activating Token Index: 175

Text #18

Max Range: 3.6050. Min Range: -3.6050

Max Act: 2.6296. Min Act: -0.0000

Data Index: 123950 (The Pile)

Max Activating Token Index: 759

Text #19

Max Range: 3.6050. Min Range: -3.6050

Max Act: 2.5116. Min Act: -0.0000

Data Index: 880937 (The Pile)

Max Activating Token Index: 734