Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: The Pile

Neuron 2522 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')

Text #0

Max Range: 0.5428. Min Range: -0.5428

Max Act: 0.5428. Min Act: -0.0000

Data Index: 1061732 (The Pile)

Max Activating Token Index: 619

Text #1

Max Range: 0.5428. Min Range: -0.5428

Max Act: 0.4639. Min Act: -0.0000

Data Index: 1544489 (The Pile)

Max Activating Token Index: 105

Text #2

Max Range: 0.5428. Min Range: -0.5428

Max Act: 0.4776. Min Act: -0.0001

Data Index: 1239772 (The Pile)

Max Activating Token Index: 508

Text #3

Max Range: 0.5428. Min Range: -0.5428

Max Act: 0.4777. Min Act: -0.0000

Data Index: 1176275 (The Pile)

Max Activating Token Index: 201

Text #4

Max Range: 0.5428. Min Range: -0.5428

Max Act: 0.4052. Min Act: -0.0001

Data Index: 1618628 (The Pile)

Max Activating Token Index: 118

Text #5

Max Range: 0.5428. Min Range: -0.5428

Max Act: 0.3570. Min Act: -0.0000

Data Index: 1970996 (The Pile)

Max Activating Token Index: 751

Text #6

Max Range: 0.5428. Min Range: -0.5428

Max Act: 0.3968. Min Act: -0.0000

Data Index: 1123943 (The Pile)

Max Activating Token Index: 347

Text #7

Max Range: 0.5428. Min Range: -0.5428

Max Act: 0.3801. Min Act: -0.0000

Data Index: 1442405 (The Pile)

Max Activating Token Index: 516

Text #8

Max Range: 0.5428. Min Range: -0.5428

Max Act: 0.3826. Min Act: -0.0000

Data Index: 1887629 (The Pile)

Max Activating Token Index: 523

Text #9

Max Range: 0.5428. Min Range: -0.5428

Max Act: 0.3354. Min Act: -0.0000

Data Index: 639819 (The Pile)

Max Activating Token Index: 229

Text #10

Max Range: 0.5428. Min Range: -0.5428

Max Act: 0.4322. Min Act: -0.0000

Data Index: 840169 (The Pile)

Max Activating Token Index: 655

Text #11

Max Range: 0.5428. Min Range: -0.5428

Max Act: 0.4049. Min Act: -0.0000

Data Index: 247239 (The Pile)

Max Activating Token Index: 853

Text #12

Max Range: 0.5428. Min Range: -0.5428

Max Act: 0.3873. Min Act: -0.0000

Data Index: 413883 (The Pile)

Max Activating Token Index: 496

Text #13

Max Range: 0.5428. Min Range: -0.5428

Max Act: 0.2484. Min Act: -0.0000

Data Index: 1890153 (The Pile)

Max Activating Token Index: 1016

Text #14

Max Range: 0.5428. Min Range: -0.5428

Max Act: 0.3322. Min Act: -0.0001

Data Index: 1439471 (The Pile)

Max Activating Token Index: 213

Text #15

Max Range: 0.5428. Min Range: -0.5428

Max Act: 0.3658. Min Act: -0.0000

Data Index: 1259019 (The Pile)

Max Activating Token Index: 289

Text #16

Max Range: 0.5428. Min Range: -0.5428

Max Act: 0.3306. Min Act: -0.0000

Data Index: 1294469 (The Pile)

Max Activating Token Index: 293

Text #17

Max Range: 0.5428. Min Range: -0.5428

Max Act: 0.3639. Min Act: -0.0000

Data Index: 647226 (The Pile)

Max Activating Token Index: 661

Text #18

Max Range: 0.5428. Min Range: -0.5428

Max Act: 0.3866. Min Act: -0.0000

Data Index: 1151658 (The Pile)

Max Activating Token Index: 787

Text #19

Max Range: 0.5428. Min Range: -0.5428

Max Act: 0.3792. Min Act: -0.0000

Data Index: 461013 (The Pile)

Max Activating Token Index: 177