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

Dataset: The Pile

Neuron 490 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5835. Min Range: -0.5835

Max Act: 0.5835. Min Act: -0.0000

Data Index: 1948627 (The Pile)

Max Activating Token Index: 493

Text #1

Max Range: 0.5835. Min Range: -0.5835

Max Act: 0.5547. Min Act: -0.0000

Data Index: 1068975 (The Pile)

Max Activating Token Index: 255

Text #2

Max Range: 0.5835. Min Range: -0.5835

Max Act: 0.5235. Min Act: -0.0000

Data Index: 873699 (The Pile)

Max Activating Token Index: 511

Text #3

Max Range: 0.5835. Min Range: -0.5835

Max Act: 0.5195. Min Act: -0.0000

Data Index: 990989 (The Pile)

Max Activating Token Index: 190

Text #4

Max Range: 0.5835. Min Range: -0.5835

Max Act: 0.5048. Min Act: -0.0000

Data Index: 786287 (The Pile)

Max Activating Token Index: 10

Text #5

Max Range: 0.5835. Min Range: -0.5835

Max Act: 0.5141. Min Act: -0.0000

Data Index: 1332152 (The Pile)

Max Activating Token Index: 115

Text #6

Max Range: 0.5835. Min Range: -0.5835

Max Act: 0.5192. Min Act: -0.0000

Data Index: 974826 (The Pile)

Max Activating Token Index: 47

Text #7

Max Range: 0.5835. Min Range: -0.5835

Max Act: 0.4957. Min Act: -0.0000

Data Index: 1286188 (The Pile)

Max Activating Token Index: 846

Text #8

Max Range: 0.5835. Min Range: -0.5835

Max Act: 0.4800. Min Act: -0.0000

Data Index: 513700 (The Pile)

Max Activating Token Index: 93

Text #9

Max Range: 0.5835. Min Range: -0.5835

Max Act: 0.4909. Min Act: -0.0000

Data Index: 1789181 (The Pile)

Max Activating Token Index: 497

Text #10

Max Range: 0.5835. Min Range: -0.5835

Max Act: 0.4770. Min Act: -0.0000

Data Index: 1536025 (The Pile)

Max Activating Token Index: 249

Text #11

Max Range: 0.5835. Min Range: -0.5835

Max Act: 0.4843. Min Act: -0.0000

Data Index: 1335174 (The Pile)

Max Activating Token Index: 479

Text #12

Max Range: 0.5835. Min Range: -0.5835

Max Act: 0.4697. Min Act: -0.0000

Data Index: 1032445 (The Pile)

Max Activating Token Index: 288

Text #13

Max Range: 0.5835. Min Range: -0.5835

Max Act: 0.4617. Min Act: -0.0000

Data Index: 298950 (The Pile)

Max Activating Token Index: 331

Text #14

Max Range: 0.5835. Min Range: -0.5835

Max Act: 0.4768. Min Act: -0.0000

Data Index: 227784 (The Pile)

Max Activating Token Index: 671

Text #15

Max Range: 0.5835. Min Range: -0.5835

Max Act: 0.4729. Min Act: -0.0000

Data Index: 1827053 (The Pile)

Max Activating Token Index: 966

Text #16

Max Range: 0.5835. Min Range: -0.5835

Max Act: 0.4126. Min Act: -0.0000

Data Index: 1660793 (The Pile)

Max Activating Token Index: 868

Text #17

Max Range: 0.5835. Min Range: -0.5835

Max Act: 0.4516. Min Act: -0.0000

Data Index: 372337 (The Pile)

Max Activating Token Index: 859

Text #18

Max Range: 0.5835. Min Range: -0.5835

Max Act: 0.4335. Min Act: -0.0000

Data Index: 1536304 (The Pile)

Max Activating Token Index: 321

Text #19

Max Range: 0.5835. Min Range: -0.5835

Max Act: 0.4421. Min Act: -0.0000

Data Index: 738283 (The Pile)

Max Activating Token Index: 318