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

Dataset: The Pile

Neuron 1621 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7998. Min Range: -0.7998

Max Act: 0.7998. Min Act: -0.0000

Data Index: 241161 (The Pile)

Max Activating Token Index: 200

Text #1

Max Range: 0.7998. Min Range: -0.7998

Max Act: 0.7441. Min Act: -0.0000

Data Index: 1374102 (The Pile)

Max Activating Token Index: 714

Text #2

Max Range: 0.7998. Min Range: -0.7998

Max Act: 0.7240. Min Act: -0.0000

Data Index: 786535 (The Pile)

Max Activating Token Index: 162

Text #3

Max Range: 0.7998. Min Range: -0.7998

Max Act: 0.7417. Min Act: -0.0000

Data Index: 1522437 (The Pile)

Max Activating Token Index: 278

Text #4

Max Range: 0.7998. Min Range: -0.7998

Max Act: 0.7189. Min Act: -0.0000

Data Index: 1372757 (The Pile)

Max Activating Token Index: 623

Text #5

Max Range: 0.7998. Min Range: -0.7998

Max Act: 0.6698. Min Act: -0.0000

Data Index: 1728579 (The Pile)

Max Activating Token Index: 77

Text #6

Max Range: 0.7998. Min Range: -0.7998

Max Act: 0.7007. Min Act: -0.0000

Data Index: 144568 (The Pile)

Max Activating Token Index: 532

Text #7

Max Range: 0.7998. Min Range: -0.7998

Max Act: 0.6975. Min Act: -0.0000

Data Index: 320031 (The Pile)

Max Activating Token Index: 102

Text #8

Max Range: 0.7998. Min Range: -0.7998

Max Act: 0.7294. Min Act: -0.0000

Data Index: 888244 (The Pile)

Max Activating Token Index: 67

Text #9

Max Range: 0.7998. Min Range: -0.7998

Max Act: 0.6710. Min Act: -0.0000

Data Index: 869395 (The Pile)

Max Activating Token Index: 352

Text #10

Max Range: 0.7998. Min Range: -0.7998

Max Act: 0.6921. Min Act: -0.0000

Data Index: 1565685 (The Pile)

Max Activating Token Index: 188

Text #11

Max Range: 0.7998. Min Range: -0.7998

Max Act: 0.6226. Min Act: -0.0000

Data Index: 319211 (The Pile)

Max Activating Token Index: 113

Text #12

Max Range: 0.7998. Min Range: -0.7998

Max Act: 0.6482. Min Act: -0.0000

Data Index: 862748 (The Pile)

Max Activating Token Index: 769

Text #13

Max Range: 0.7998. Min Range: -0.7998

Max Act: 0.6762. Min Act: -0.0000

Data Index: 1557592 (The Pile)

Max Activating Token Index: 290

Text #14

Max Range: 0.7998. Min Range: -0.7998

Max Act: 0.6671. Min Act: -0.0000

Data Index: 1294299 (The Pile)

Max Activating Token Index: 69

Text #15

Max Range: 0.7998. Min Range: -0.7998

Max Act: 0.6148. Min Act: -0.0000

Data Index: 834802 (The Pile)

Max Activating Token Index: 237

Text #16

Max Range: 0.7998. Min Range: -0.7998

Max Act: 0.6176. Min Act: -0.0000

Data Index: 191459 (The Pile)

Max Activating Token Index: 485

Text #17

Max Range: 0.7998. Min Range: -0.7998

Max Act: 0.6788. Min Act: -0.0000

Data Index: 320597 (The Pile)

Max Activating Token Index: 91

Text #18

Max Range: 0.7998. Min Range: -0.7998

Max Act: 0.6327. Min Act: -0.0000

Data Index: 448814 (The Pile)

Max Activating Token Index: 277

Text #19

Max Range: 0.7998. Min Range: -0.7998

Max Act: 0.6281. Min Act: -0.0000

Data Index: 865916 (The Pile)

Max Activating Token Index: 599