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

Dataset: The Pile

Neuron 3091 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: 0.8653. Min Range: -0.8653

Max Act: 0.8653. Min Act: -0.0000

Data Index: 1385501 (The Pile)

Max Activating Token Index: 82

Text #1

Max Range: 0.8653. Min Range: -0.8653

Max Act: 0.8310. Min Act: -0.0000

Data Index: 387374 (The Pile)

Max Activating Token Index: 80

Text #2

Max Range: 0.8653. Min Range: -0.8653

Max Act: 0.8183. Min Act: -0.0000

Data Index: 1712175 (The Pile)

Max Activating Token Index: 171

Text #3

Max Range: 0.8653. Min Range: -0.8653

Max Act: 0.8451. Min Act: -0.0000

Data Index: 1339690 (The Pile)

Max Activating Token Index: 409

Text #4

Max Range: 0.8653. Min Range: -0.8653

Max Act: 0.7634. Min Act: -0.0000

Data Index: 1482894 (The Pile)

Max Activating Token Index: 414

Text #5

Max Range: 0.8653. Min Range: -0.8653

Max Act: 0.7268. Min Act: -0.0000

Data Index: 1436748 (The Pile)

Max Activating Token Index: 365

Text #6

Max Range: 0.8653. Min Range: -0.8653

Max Act: 0.7048. Min Act: -0.0000

Data Index: 416073 (The Pile)

Max Activating Token Index: 268

Text #7

Max Range: 0.8653. Min Range: -0.8653

Max Act: 0.6993. Min Act: 0.0000

Data Index: 1572766 (The Pile)

Max Activating Token Index: 145

Text #8

Max Range: 0.8653. Min Range: -0.8653

Max Act: 0.6761. Min Act: -0.0000

Data Index: 378184 (The Pile)

Max Activating Token Index: 268

Text #9

Max Range: 0.8653. Min Range: -0.8653

Max Act: 0.6756. Min Act: -0.0000

Data Index: 598258 (The Pile)

Max Activating Token Index: 555

Text #10

Max Range: 0.8653. Min Range: -0.8653

Max Act: 0.6608. Min Act: -0.0000

Data Index: 1153479 (The Pile)

Max Activating Token Index: 79

Text #11

Max Range: 0.8653. Min Range: -0.8653

Max Act: 0.6992. Min Act: -0.0000

Data Index: 1449147 (The Pile)

Max Activating Token Index: 628

Text #12

Max Range: 0.8653. Min Range: -0.8653

Max Act: 0.7134. Min Act: 0.0000

Data Index: 124833 (The Pile)

Max Activating Token Index: 268

Text #13

Max Range: 0.8653. Min Range: -0.8653

Max Act: 0.5953. Min Act: -0.0000

Data Index: 1499936 (The Pile)

Max Activating Token Index: 893

Text #14

Max Range: 0.8653. Min Range: -0.8653

Max Act: 0.5973. Min Act: -0.0000

Data Index: 1098314 (The Pile)

Max Activating Token Index: 792

Text #15

Max Range: 0.8653. Min Range: -0.8653

Max Act: 0.6486. Min Act: -0.0000

Data Index: 1318043 (The Pile)

Max Activating Token Index: 331

Text #16

Max Range: 0.8653. Min Range: -0.8653

Max Act: 0.6003. Min Act: -0.0000

Data Index: 1926550 (The Pile)

Max Activating Token Index: 668

Text #17

Max Range: 0.8653. Min Range: -0.8653

Max Act: 0.6148. Min Act: -0.0000

Data Index: 1038200 (The Pile)

Max Activating Token Index: 427

Text #18

Max Range: 0.8653. Min Range: -0.8653

Max Act: 0.6659. Min Act: -0.0000

Data Index: 1192904 (The Pile)

Max Activating Token Index: 476

Text #19

Max Range: 0.8653. Min Range: -0.8653

Max Act: 0.7079. Min Act: -0.0000

Data Index: 1097831 (The Pile)

Max Activating Token Index: 526