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

Dataset: The Pile

Neuron 3021 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1998. Min Range: -1.1998

Max Act: 1.1998. Min Act: -0.0000

Data Index: 1466169 (The Pile)

Max Activating Token Index: 55

Text #1

Max Range: 1.1998. Min Range: -1.1998

Max Act: 1.0102. Min Act: -0.0000

Data Index: 983280 (The Pile)

Max Activating Token Index: 183

Text #2

Max Range: 1.1998. Min Range: -1.1998

Max Act: 1.1836. Min Act: -0.0000

Data Index: 1117190 (The Pile)

Max Activating Token Index: 85

Text #3

Max Range: 1.1998. Min Range: -1.1998

Max Act: 1.1260. Min Act: -0.0000

Data Index: 1626038 (The Pile)

Max Activating Token Index: 602

Text #4

Max Range: 1.1998. Min Range: -1.1998

Max Act: 1.1198. Min Act: -0.0000

Data Index: 71286 (The Pile)

Max Activating Token Index: 615

Text #5

Max Range: 1.1998. Min Range: -1.1998

Max Act: 1.1209. Min Act: -0.0000

Data Index: 518476 (The Pile)

Max Activating Token Index: 759

Text #6

Max Range: 1.1998. Min Range: -1.1998

Max Act: 1.1108. Min Act: -0.0000

Data Index: 1236557 (The Pile)

Max Activating Token Index: 98

Text #7

Max Range: 1.1998. Min Range: -1.1998

Max Act: 1.0839. Min Act: -0.0000

Data Index: 1155487 (The Pile)

Max Activating Token Index: 53

Text #8

Max Range: 1.1998. Min Range: -1.1998

Max Act: 1.0489. Min Act: -0.0000

Data Index: 496440 (The Pile)

Max Activating Token Index: 1008

Text #9

Max Range: 1.1998. Min Range: -1.1998

Max Act: 1.1860. Min Act: -0.0000

Data Index: 133593 (The Pile)

Max Activating Token Index: 617

Text #10

Max Range: 1.1998. Min Range: -1.1998

Max Act: 1.0217. Min Act: -0.0000

Data Index: 157825 (The Pile)

Max Activating Token Index: 84

Text #11

Max Range: 1.1998. Min Range: -1.1998

Max Act: 0.9998. Min Act: -0.0000

Data Index: 41658 (The Pile)

Max Activating Token Index: 854

Text #12

Max Range: 1.1998. Min Range: -1.1998

Max Act: 0.7800. Min Act: -0.0000

Data Index: 1336661 (The Pile)

Max Activating Token Index: 263

Text #13

Max Range: 1.1998. Min Range: -1.1998

Max Act: 1.0004. Min Act: -0.0000

Data Index: 312847 (The Pile)

Max Activating Token Index: 573

Text #14

Max Range: 1.1998. Min Range: -1.1998

Max Act: 0.9822. Min Act: -0.0000

Data Index: 677656 (The Pile)

Max Activating Token Index: 328

Text #15

Max Range: 1.1998. Min Range: -1.1998

Max Act: 0.9241. Min Act: -0.0000

Data Index: 477130 (The Pile)

Max Activating Token Index: 133

Text #16

Max Range: 1.1998. Min Range: -1.1998

Max Act: 0.9304. Min Act: -0.0000

Data Index: 1892323 (The Pile)

Max Activating Token Index: 448

Text #17

Max Range: 1.1998. Min Range: -1.1998

Max Act: 0.9483. Min Act: -0.0000

Data Index: 229993 (The Pile)

Max Activating Token Index: 276

Text #18

Max Range: 1.1998. Min Range: -1.1998

Max Act: 0.9078. Min Act: -0.0000

Data Index: 1457983 (The Pile)

Max Activating Token Index: 132

Text #19

Max Range: 1.1998. Min Range: -1.1998

Max Act: 0.8980. Min Act: -0.0000

Data Index: 222085 (The Pile)

Max Activating Token Index: 940