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

Dataset: The Pile

Neuron 765 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: 1.1784. Min Range: -1.1784

Max Act: 1.1784. Min Act: -0.0000

Data Index: 1069291 (The Pile)

Max Activating Token Index: 754

Text #1

Max Range: 1.1784. Min Range: -1.1784

Max Act: 1.1071. Min Act: -0.0000

Data Index: 1140636 (The Pile)

Max Activating Token Index: 832

Text #2

Max Range: 1.1784. Min Range: -1.1784

Max Act: 1.0276. Min Act: -0.0000

Data Index: 492986 (The Pile)

Max Activating Token Index: 478

Text #3

Max Range: 1.1784. Min Range: -1.1784

Max Act: 1.0213. Min Act: -0.0000

Data Index: 51020 (The Pile)

Max Activating Token Index: 685

Text #4

Max Range: 1.1784. Min Range: -1.1784

Max Act: 1.0114. Min Act: -0.0000

Data Index: 332114 (The Pile)

Max Activating Token Index: 274

Text #5

Max Range: 1.1784. Min Range: -1.1784

Max Act: 1.0546. Min Act: -0.0000

Data Index: 1725793 (The Pile)

Max Activating Token Index: 663

Text #6

Max Range: 1.1784. Min Range: -1.1784

Max Act: 0.9300. Min Act: -0.0000

Data Index: 1047540 (The Pile)

Max Activating Token Index: 523

Text #7

Max Range: 1.1784. Min Range: -1.1784

Max Act: 0.9909. Min Act: -0.0000

Data Index: 1490814 (The Pile)

Max Activating Token Index: 166

Text #8

Max Range: 1.1784. Min Range: -1.1784

Max Act: 0.9793. Min Act: -0.0000

Data Index: 802643 (The Pile)

Max Activating Token Index: 328

Text #9

Max Range: 1.1784. Min Range: -1.1784

Max Act: 1.0136. Min Act: -0.0000

Data Index: 1835818 (The Pile)

Max Activating Token Index: 264

Text #10

Max Range: 1.1784. Min Range: -1.1784

Max Act: 0.8963. Min Act: -0.0000

Data Index: 1055948 (The Pile)

Max Activating Token Index: 766

Text #11

Max Range: 1.1784. Min Range: -1.1784

Max Act: 0.9205. Min Act: -0.0000

Data Index: 1183142 (The Pile)

Max Activating Token Index: 633

Text #12

Max Range: 1.1784. Min Range: -1.1784

Max Act: 0.9005. Min Act: -0.0000

Data Index: 1734225 (The Pile)

Max Activating Token Index: 545

Text #13

Max Range: 1.1784. Min Range: -1.1784

Max Act: 0.8986. Min Act: -0.0000

Data Index: 1714770 (The Pile)

Max Activating Token Index: 607

Text #14

Max Range: 1.1784. Min Range: -1.1784

Max Act: 0.9417. Min Act: -0.0000

Data Index: 718220 (The Pile)

Max Activating Token Index: 111

Text #15

Max Range: 1.1784. Min Range: -1.1784

Max Act: 0.7975. Min Act: -0.0000

Data Index: 1813964 (The Pile)

Max Activating Token Index: 219

Text #16

Max Range: 1.1784. Min Range: -1.1784

Max Act: 0.8619. Min Act: -0.0000

Data Index: 414749 (The Pile)

Max Activating Token Index: 626

Text #17

Max Range: 1.1784. Min Range: -1.1784

Max Act: 0.8472. Min Act: -0.0000

Data Index: 723418 (The Pile)

Max Activating Token Index: 706

Text #18

Max Range: 1.1784. Min Range: -1.1784

Max Act: 0.9085. Min Act: -0.0000

Data Index: 314261 (The Pile)

Max Activating Token Index: 498

Text #19

Max Range: 1.1784. Min Range: -1.1784

Max Act: 0.8002. Min Act: -0.0000

Data Index: 1942163 (The Pile)

Max Activating Token Index: 786