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

Dataset: The Pile

Neuron 3315 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7112. Min Range: -1.7112

Max Act: 1.7112. Min Act: -0.0000

Data Index: 957489 (The Pile)

Max Activating Token Index: 482

Text #1

Max Range: 1.7112. Min Range: -1.7112

Max Act: 1.6237. Min Act: -0.0000

Data Index: 146533 (The Pile)

Max Activating Token Index: 109

Text #2

Max Range: 1.7112. Min Range: -1.7112

Max Act: 1.3829. Min Act: -0.0000

Data Index: 1746367 (The Pile)

Max Activating Token Index: 971

Text #3

Max Range: 1.7112. Min Range: -1.7112

Max Act: 1.3611. Min Act: -0.0000

Data Index: 650129 (The Pile)

Max Activating Token Index: 979

Text #4

Max Range: 1.7112. Min Range: -1.7112

Max Act: 1.2359. Min Act: -0.0000

Data Index: 619490 (The Pile)

Max Activating Token Index: 84

Text #5

Max Range: 1.7112. Min Range: -1.7112

Max Act: 1.2000. Min Act: -0.0000

Data Index: 83199 (The Pile)

Max Activating Token Index: 710

Text #6

Max Range: 1.7112. Min Range: -1.7112

Max Act: 1.1930. Min Act: -0.0000

Data Index: 448975 (The Pile)

Max Activating Token Index: 789

Text #7

Max Range: 1.7112. Min Range: -1.7112

Max Act: 1.2737. Min Act: -0.0000

Data Index: 754362 (The Pile)

Max Activating Token Index: 415

Text #8

Max Range: 1.7112. Min Range: -1.7112

Max Act: 1.2922. Min Act: -0.0000

Data Index: 276151 (The Pile)

Max Activating Token Index: 930

Text #9

Max Range: 1.7112. Min Range: -1.7112

Max Act: 1.1733. Min Act: -0.0000

Data Index: 1084676 (The Pile)

Max Activating Token Index: 286

Text #10

Max Range: 1.7112. Min Range: -1.7112

Max Act: 1.1524. Min Act: -0.0000

Data Index: 376851 (The Pile)

Max Activating Token Index: 335

Text #11

Max Range: 1.7112. Min Range: -1.7112

Max Act: 1.0227. Min Act: -0.0000

Data Index: 1681800 (The Pile)

Max Activating Token Index: 137

Text #12

Max Range: 1.7112. Min Range: -1.7112

Max Act: 1.1611. Min Act: -0.0000

Data Index: 1662970 (The Pile)

Max Activating Token Index: 200

Text #13

Max Range: 1.7112. Min Range: -1.7112

Max Act: 0.9997. Min Act: -0.0000

Data Index: 241495 (The Pile)

Max Activating Token Index: 382

Text #14

Max Range: 1.7112. Min Range: -1.7112

Max Act: 1.0236. Min Act: -0.0000

Data Index: 1944200 (The Pile)

Max Activating Token Index: 127

Text #15

Max Range: 1.7112. Min Range: -1.7112

Max Act: 0.9793. Min Act: -0.0000

Data Index: 1436503 (The Pile)

Max Activating Token Index: 676

Text #16

Max Range: 1.7112. Min Range: -1.7112

Max Act: 1.0140. Min Act: -0.0000

Data Index: 814222 (The Pile)

Max Activating Token Index: 176

Text #17

Max Range: 1.7112. Min Range: -1.7112

Max Act: 0.8865. Min Act: -0.0000

Data Index: 464709 (The Pile)

Max Activating Token Index: 440

Text #18

Max Range: 1.7112. Min Range: -1.7112

Max Act: 1.0405. Min Act: -0.0000

Data Index: 1483561 (The Pile)

Max Activating Token Index: 79

Text #19

Max Range: 1.7112. Min Range: -1.7112

Max Act: 0.9403. Min Act: -0.0000

Data Index: 315091 (The Pile)

Max Activating Token Index: 153