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

Dataset: The Pile

Neuron 3568 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7466. Min Range: -1.7466

Max Act: 1.7466. Min Act: -0.0000

Data Index: 82854 (The Pile)

Max Activating Token Index: 141

Text #1

Max Range: 1.7466. Min Range: -1.7466

Max Act: 1.4850. Min Act: -0.0000

Data Index: 1098536 (The Pile)

Max Activating Token Index: 355

Text #2

Max Range: 1.7466. Min Range: -1.7466

Max Act: 1.4610. Min Act: -0.0000

Data Index: 475024 (The Pile)

Max Activating Token Index: 132

Text #3

Max Range: 1.7466. Min Range: -1.7466

Max Act: 1.3805. Min Act: -0.0000

Data Index: 1079643 (The Pile)

Max Activating Token Index: 92

Text #4

Max Range: 1.7466. Min Range: -1.7466

Max Act: 1.3759. Min Act: -0.0000

Data Index: 437251 (The Pile)

Max Activating Token Index: 748

Text #5

Max Range: 1.7466. Min Range: -1.7466

Max Act: 1.4487. Min Act: -0.0000

Data Index: 1442986 (The Pile)

Max Activating Token Index: 373

Text #6

Max Range: 1.7466. Min Range: -1.7466

Max Act: 1.3133. Min Act: -0.0000

Data Index: 947528 (The Pile)

Max Activating Token Index: 117

Text #7

Max Range: 1.7466. Min Range: -1.7466

Max Act: 1.2355. Min Act: -0.0000

Data Index: 86866 (The Pile)

Max Activating Token Index: 198

Text #8

Max Range: 1.7466. Min Range: -1.7466

Max Act: 1.3813. Min Act: -0.0000

Data Index: 832153 (The Pile)

Max Activating Token Index: 602

Text #9

Max Range: 1.7466. Min Range: -1.7466

Max Act: 1.2101. Min Act: -0.0000

Data Index: 1306732 (The Pile)

Max Activating Token Index: 161

Text #10

Max Range: 1.7466. Min Range: -1.7466

Max Act: 1.1816. Min Act: -0.0000

Data Index: 1181331 (The Pile)

Max Activating Token Index: 560

Text #11

Max Range: 1.7466. Min Range: -1.7466

Max Act: 1.1708. Min Act: -0.0000

Data Index: 1037205 (The Pile)

Max Activating Token Index: 110

Text #12

Max Range: 1.7466. Min Range: -1.7466

Max Act: 1.1001. Min Act: -0.0000

Data Index: 1429826 (The Pile)

Max Activating Token Index: 235

Text #13

Max Range: 1.7466. Min Range: -1.7466

Max Act: 1.1391. Min Act: -0.0000

Data Index: 1569638 (The Pile)

Max Activating Token Index: 239

Text #14

Max Range: 1.7466. Min Range: -1.7466

Max Act: 1.2141. Min Act: -0.0000

Data Index: 806520 (The Pile)

Max Activating Token Index: 708

Text #15

Max Range: 1.7466. Min Range: -1.7466

Max Act: 1.1350. Min Act: -0.0000

Data Index: 972620 (The Pile)

Max Activating Token Index: 364

Text #16

Max Range: 1.7466. Min Range: -1.7466

Max Act: 1.0902. Min Act: -0.0000

Data Index: 1163473 (The Pile)

Max Activating Token Index: 704

Text #17

Max Range: 1.7466. Min Range: -1.7466

Max Act: 1.1518. Min Act: -0.0000

Data Index: 519998 (The Pile)

Max Activating Token Index: 1013

Text #18

Max Range: 1.7466. Min Range: -1.7466

Max Act: 1.1312. Min Act: -0.0000

Data Index: 1730817 (The Pile)

Max Activating Token Index: 455

Text #19

Max Range: 1.7466. Min Range: -1.7466

Max Act: 1.1769. Min Act: -0.0000

Data Index: 294277 (The Pile)

Max Activating Token Index: 370