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

Dataset: The Pile

Neuron 2251 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5727. Min Range: -0.5727

Max Act: 0.5727. Min Act: -0.0000

Data Index: 304831 (The Pile)

Max Activating Token Index: 961

Text #1

Max Range: 0.5727. Min Range: -0.5727

Max Act: 0.5464. Min Act: -0.0000

Data Index: 470310 (The Pile)

Max Activating Token Index: 654

Text #2

Max Range: 0.5727. Min Range: -0.5727

Max Act: 0.5098. Min Act: -0.0000

Data Index: 894239 (The Pile)

Max Activating Token Index: 81

Text #3

Max Range: 0.5727. Min Range: -0.5727

Max Act: 0.4463. Min Act: -0.0001

Data Index: 1830043 (The Pile)

Max Activating Token Index: 880

Text #4

Max Range: 0.5727. Min Range: -0.5727

Max Act: 0.4554. Min Act: -0.0000

Data Index: 1739072 (The Pile)

Max Activating Token Index: 495

Text #5

Max Range: 0.5727. Min Range: -0.5727

Max Act: 0.4763. Min Act: -0.0000

Data Index: 127474 (The Pile)

Max Activating Token Index: 508

Text #6

Max Range: 0.5727. Min Range: -0.5727

Max Act: 0.4388. Min Act: -0.0000

Data Index: 792596 (The Pile)

Max Activating Token Index: 637

Text #7

Max Range: 0.5727. Min Range: -0.5727

Max Act: 0.4247. Min Act: -0.0000

Data Index: 1308800 (The Pile)

Max Activating Token Index: 542

Text #8

Max Range: 0.5727. Min Range: -0.5727

Max Act: 0.3861. Min Act: -0.0000

Data Index: 398441 (The Pile)

Max Activating Token Index: 857

Text #9

Max Range: 0.5727. Min Range: -0.5727

Max Act: 0.3701. Min Act: -0.0000

Data Index: 1736900 (The Pile)

Max Activating Token Index: 614

Text #10

Max Range: 0.5727. Min Range: -0.5727

Max Act: 0.3781. Min Act: -0.0000

Data Index: 1360148 (The Pile)

Max Activating Token Index: 57

Text #11

Max Range: 0.5727. Min Range: -0.5727

Max Act: 0.3330. Min Act: -0.0000

Data Index: 607941 (The Pile)

Max Activating Token Index: 753

Text #12

Max Range: 0.5727. Min Range: -0.5727

Max Act: 0.3633. Min Act: -0.0000

Data Index: 1637215 (The Pile)

Max Activating Token Index: 40

Text #13

Max Range: 0.5727. Min Range: -0.5727

Max Act: 0.3429. Min Act: -0.0000

Data Index: 815383 (The Pile)

Max Activating Token Index: 492

Text #14

Max Range: 0.5727. Min Range: -0.5727

Max Act: 0.3130. Min Act: -0.0000

Data Index: 1599373 (The Pile)

Max Activating Token Index: 775

Text #15

Max Range: 0.5727. Min Range: -0.5727

Max Act: 0.3222. Min Act: -0.0000

Data Index: 1006604 (The Pile)

Max Activating Token Index: 820

Text #16

Max Range: 0.5727. Min Range: -0.5727

Max Act: 0.3191. Min Act: -0.0000

Data Index: 920062 (The Pile)

Max Activating Token Index: 520

Text #17

Max Range: 0.5727. Min Range: -0.5727

Max Act: 0.3130. Min Act: -0.0000

Data Index: 1059151 (The Pile)

Max Activating Token Index: 922

Text #18

Max Range: 0.5727. Min Range: -0.5727

Max Act: 0.3046. Min Act: -0.0000

Data Index: 1271438 (The Pile)

Max Activating Token Index: 695

Text #19

Max Range: 0.5727. Min Range: -0.5727

Max Act: 0.3014. Min Act: -0.0000

Data Index: 418850 (The Pile)

Max Activating Token Index: 55