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

Dataset: The Pile

Neuron 3314 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: 0.5831. Min Range: -0.5831

Max Act: 0.5831. Min Act: -0.0000

Data Index: 997363 (The Pile)

Max Activating Token Index: 341

Text #1

Max Range: 0.5831. Min Range: -0.5831

Max Act: 0.5396. Min Act: -0.0000

Data Index: 1651762 (The Pile)

Max Activating Token Index: 539

Text #2

Max Range: 0.5831. Min Range: -0.5831

Max Act: 0.5547. Min Act: 0.0000

Data Index: 1000767 (The Pile)

Max Activating Token Index: 131

Text #3

Max Range: 0.5831. Min Range: -0.5831

Max Act: 0.5245. Min Act: -0.0000

Data Index: 1476379 (The Pile)

Max Activating Token Index: 870

Text #4

Max Range: 0.5831. Min Range: -0.5831

Max Act: 0.4917. Min Act: -0.0000

Data Index: 1357334 (The Pile)

Max Activating Token Index: 837

Text #5

Max Range: 0.5831. Min Range: -0.5831

Max Act: 0.5175. Min Act: -0.0000

Data Index: 143347 (The Pile)

Max Activating Token Index: 552

Text #6

Max Range: 0.5831. Min Range: -0.5831

Max Act: 0.5232. Min Act: -0.0000

Data Index: 39849 (The Pile)

Max Activating Token Index: 174

Text #7

Max Range: 0.5831. Min Range: -0.5831

Max Act: 0.5086. Min Act: -0.0000

Data Index: 989532 (The Pile)

Max Activating Token Index: 856

Text #8

Max Range: 0.5831. Min Range: -0.5831

Max Act: 0.5161. Min Act: -0.0000

Data Index: 1351377 (The Pile)

Max Activating Token Index: 628

Text #9

Max Range: 0.5831. Min Range: -0.5831

Max Act: 0.4631. Min Act: 0.0000

Data Index: 1457423 (The Pile)

Max Activating Token Index: 185

Text #10

Max Range: 0.5831. Min Range: -0.5831

Max Act: 0.4234. Min Act: -0.0000

Data Index: 563632 (The Pile)

Max Activating Token Index: 261

Text #11

Max Range: 0.5831. Min Range: -0.5831

Max Act: 0.4527. Min Act: -0.0000

Data Index: 1385542 (The Pile)

Max Activating Token Index: 413

Text #12

Max Range: 0.5831. Min Range: -0.5831

Max Act: 0.4388. Min Act: -0.0000

Data Index: 1686380 (The Pile)

Max Activating Token Index: 818

Text #13

Max Range: 0.5831. Min Range: -0.5831

Max Act: 0.4382. Min Act: 0.0000

Data Index: 473531 (The Pile)

Max Activating Token Index: 418

Text #14

Max Range: 0.5831. Min Range: -0.5831

Max Act: 0.4743. Min Act: -0.0000

Data Index: 356956 (The Pile)

Max Activating Token Index: 79

Text #15

Max Range: 0.5831. Min Range: -0.5831

Max Act: 0.4145. Min Act: -0.0000

Data Index: 1040550 (The Pile)

Max Activating Token Index: 640

Text #16

Max Range: 0.5831. Min Range: -0.5831

Max Act: 0.4162. Min Act: -0.0000

Data Index: 1563174 (The Pile)

Max Activating Token Index: 207

Text #17

Max Range: 0.5831. Min Range: -0.5831

Max Act: 0.4480. Min Act: -0.0000

Data Index: 1446101 (The Pile)

Max Activating Token Index: 67

Text #18

Max Range: 0.5831. Min Range: -0.5831

Max Act: 0.3866. Min Act: -0.0000

Data Index: 1053802 (The Pile)

Max Activating Token Index: 415

Text #19

Max Range: 0.5831. Min Range: -0.5831

Max Act: 0.4252. Min Act: -0.0000

Data Index: 899516 (The Pile)

Max Activating Token Index: 868