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

Dataset: The Pile

Neuron 708 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: 0.7042. Min Range: -0.7042

Max Act: 0.6316. Min Act: -0.0000

Data Index: 1989978 (The Pile)

Max Activating Token Index: 485

Text #1

Max Range: 0.7042. Min Range: -0.7042

Max Act: 0.7042. Min Act: -0.0000

Data Index: 1779859 (The Pile)

Max Activating Token Index: 740

Text #2

Max Range: 0.7042. Min Range: -0.7042

Max Act: 0.5942. Min Act: -0.0000

Data Index: 1245526 (The Pile)

Max Activating Token Index: 184

Text #3

Max Range: 0.7042. Min Range: -0.7042

Max Act: 0.6063. Min Act: -0.0000

Data Index: 536678 (The Pile)

Max Activating Token Index: 267

Text #4

Max Range: 0.7042. Min Range: -0.7042

Max Act: 0.6270. Min Act: -0.0000

Data Index: 1451184 (The Pile)

Max Activating Token Index: 715

Text #5

Max Range: 0.7042. Min Range: -0.7042

Max Act: 0.5423. Min Act: -0.0000

Data Index: 1306621 (The Pile)

Max Activating Token Index: 752

Text #6

Max Range: 0.7042. Min Range: -0.7042

Max Act: 0.5791. Min Act: -0.0000

Data Index: 1961965 (The Pile)

Max Activating Token Index: 49

Text #7

Max Range: 0.7042. Min Range: -0.7042

Max Act: 0.5977. Min Act: -0.0000

Data Index: 445766 (The Pile)

Max Activating Token Index: 944

Text #8

Max Range: 0.7042. Min Range: -0.7042

Max Act: 0.6265. Min Act: -0.0000

Data Index: 554874 (The Pile)

Max Activating Token Index: 43

Text #9

Max Range: 0.7042. Min Range: -0.7042

Max Act: 0.5227. Min Act: -0.0000

Data Index: 930791 (The Pile)

Max Activating Token Index: 817

Text #10

Max Range: 0.7042. Min Range: -0.7042

Max Act: 0.5876. Min Act: -0.0000

Data Index: 638279 (The Pile)

Max Activating Token Index: 32

Text #11

Max Range: 0.7042. Min Range: -0.7042

Max Act: 0.5294. Min Act: -0.0000

Data Index: 1566387 (The Pile)

Max Activating Token Index: 487

Text #12

Max Range: 0.7042. Min Range: -0.7042

Max Act: 0.5107. Min Act: -0.0000

Data Index: 1430543 (The Pile)

Max Activating Token Index: 960

Text #13

Max Range: 0.7042. Min Range: -0.7042

Max Act: 0.5435. Min Act: -0.0000

Data Index: 1623764 (The Pile)

Max Activating Token Index: 300

Text #14

Max Range: 0.7042. Min Range: -0.7042

Max Act: 0.4317. Min Act: -0.0000

Data Index: 628283 (The Pile)

Max Activating Token Index: 969

Text #15

Max Range: 0.7042. Min Range: -0.7042

Max Act: 0.4525. Min Act: -0.0000

Data Index: 945641 (The Pile)

Max Activating Token Index: 49

Text #16

Max Range: 0.7042. Min Range: -0.7042

Max Act: 0.4281. Min Act: -0.0000

Data Index: 571610 (The Pile)

Max Activating Token Index: 773

Text #17

Max Range: 0.7042. Min Range: -0.7042

Max Act: 0.4818. Min Act: -0.0000

Data Index: 546680 (The Pile)

Max Activating Token Index: 300

Text #18

Max Range: 0.7042. Min Range: -0.7042

Max Act: 0.4822. Min Act: -0.0000

Data Index: 1242395 (The Pile)

Max Activating Token Index: 353

Text #19

Max Range: 0.7042. Min Range: -0.7042

Max Act: 0.4622. Min Act: -0.0000

Data Index: 941504 (The Pile)

Max Activating Token Index: 8