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

Dataset: The Pile

Neuron 2926 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6986. Min Range: -0.6986

Max Act: 0.6854. Min Act: -0.0000

Data Index: 1767829 (The Pile)

Max Activating Token Index: 360

Text #1

Max Range: 0.6986. Min Range: -0.6986

Max Act: 0.5838. Min Act: -0.0000

Data Index: 1985101 (The Pile)

Max Activating Token Index: 705

Text #2

Max Range: 0.6986. Min Range: -0.6986

Max Act: 0.6715. Min Act: -0.0000

Data Index: 1616164 (The Pile)

Max Activating Token Index: 128

Text #3

Max Range: 0.6986. Min Range: -0.6986

Max Act: 0.6986. Min Act: 0.0000

Data Index: 1899485 (The Pile)

Max Activating Token Index: 52

Text #4

Max Range: 0.6986. Min Range: -0.6986

Max Act: 0.6020. Min Act: -0.0000

Data Index: 1477246 (The Pile)

Max Activating Token Index: 157

Text #5

Max Range: 0.6986. Min Range: -0.6986

Max Act: 0.6116. Min Act: -0.0000

Data Index: 90377 (The Pile)

Max Activating Token Index: 1019

Text #6

Max Range: 0.6986. Min Range: -0.6986

Max Act: 0.5577. Min Act: -0.0000

Data Index: 1164793 (The Pile)

Max Activating Token Index: 290

Text #7

Max Range: 0.6986. Min Range: -0.6986

Max Act: 0.6243. Min Act: -0.0000

Data Index: 866663 (The Pile)

Max Activating Token Index: 859

Text #8

Max Range: 0.6986. Min Range: -0.6986

Max Act: 0.6515. Min Act: -0.0000

Data Index: 1153054 (The Pile)

Max Activating Token Index: 837

Text #9

Max Range: 0.6986. Min Range: -0.6986

Max Act: 0.5789. Min Act: -0.0000

Data Index: 1667210 (The Pile)

Max Activating Token Index: 803

Text #10

Max Range: 0.6986. Min Range: -0.6986

Max Act: 0.5657. Min Act: -0.0000

Data Index: 86115 (The Pile)

Max Activating Token Index: 937

Text #11

Max Range: 0.6986. Min Range: -0.6986

Max Act: 0.6189. Min Act: -0.0000

Data Index: 1172098 (The Pile)

Max Activating Token Index: 161

Text #12

Max Range: 0.6986. Min Range: -0.6986

Max Act: 0.5377. Min Act: -0.0000

Data Index: 1824436 (The Pile)

Max Activating Token Index: 220

Text #13

Max Range: 0.6986. Min Range: -0.6986

Max Act: 0.4444. Min Act: -0.0000

Data Index: 206146 (The Pile)

Max Activating Token Index: 624

Text #14

Max Range: 0.6986. Min Range: -0.6986

Max Act: 0.5140. Min Act: -0.0000

Data Index: 1480787 (The Pile)

Max Activating Token Index: 333

Text #15

Max Range: 0.6986. Min Range: -0.6986

Max Act: 0.5026. Min Act: -0.0000

Data Index: 57983 (The Pile)

Max Activating Token Index: 609

Text #16

Max Range: 0.6986. Min Range: -0.6986

Max Act: 0.5522. Min Act: -0.0000

Data Index: 1012865 (The Pile)

Max Activating Token Index: 61

Text #17

Max Range: 0.6986. Min Range: -0.6986

Max Act: 0.5762. Min Act: -0.0000

Data Index: 150930 (The Pile)

Max Activating Token Index: 958

Text #18

Max Range: 0.6986. Min Range: -0.6986

Max Act: 0.5392. Min Act: -0.0000

Data Index: 1594666 (The Pile)

Max Activating Token Index: 697

Text #19

Max Range: 0.6986. Min Range: -0.6986

Max Act: 0.5285. Min Act: -0.0000

Data Index: 161129 (The Pile)

Max Activating Token Index: 183