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

Dataset: The Pile

Neuron 1554 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: 0.6643. Min Range: -0.6643

Max Act: 0.6643. Min Act: -0.0000

Data Index: 1037391 (The Pile)

Max Activating Token Index: 369

Text #1

Max Range: 0.6643. Min Range: -0.6643

Max Act: 0.6409. Min Act: -0.0000

Data Index: 589945 (The Pile)

Max Activating Token Index: 678

Text #2

Max Range: 0.6643. Min Range: -0.6643

Max Act: 0.6383. Min Act: -0.0000

Data Index: 772163 (The Pile)

Max Activating Token Index: 383

Text #3

Max Range: 0.6643. Min Range: -0.6643

Max Act: 0.6185. Min Act: -0.0000

Data Index: 1987136 (The Pile)

Max Activating Token Index: 580

Text #4

Max Range: 0.6643. Min Range: -0.6643

Max Act: 0.5984. Min Act: -0.0000

Data Index: 1644126 (The Pile)

Max Activating Token Index: 809

Text #5

Max Range: 0.6643. Min Range: -0.6643

Max Act: 0.6457. Min Act: -0.0000

Data Index: 61633 (The Pile)

Max Activating Token Index: 535

Text #6

Max Range: 0.6643. Min Range: -0.6643

Max Act: 0.5936. Min Act: -0.0000

Data Index: 155975 (The Pile)

Max Activating Token Index: 898

Text #7

Max Range: 0.6643. Min Range: -0.6643

Max Act: 0.5659. Min Act: -0.0000

Data Index: 1072156 (The Pile)

Max Activating Token Index: 101

Text #8

Max Range: 0.6643. Min Range: -0.6643

Max Act: 0.5763. Min Act: -0.0000

Data Index: 1876534 (The Pile)

Max Activating Token Index: 486

Text #9

Max Range: 0.6643. Min Range: -0.6643

Max Act: 0.5718. Min Act: -0.0000

Data Index: 215438 (The Pile)

Max Activating Token Index: 198

Text #10

Max Range: 0.6643. Min Range: -0.6643

Max Act: 0.6034. Min Act: -0.0000

Data Index: 1719233 (The Pile)

Max Activating Token Index: 618

Text #11

Max Range: 0.6643. Min Range: -0.6643

Max Act: 0.5808. Min Act: -0.0000

Data Index: 1548669 (The Pile)

Max Activating Token Index: 513

Text #12

Max Range: 0.6643. Min Range: -0.6643

Max Act: 0.5489. Min Act: -0.0000

Data Index: 1114660 (The Pile)

Max Activating Token Index: 425

Text #13

Max Range: 0.6643. Min Range: -0.6643

Max Act: 0.5383. Min Act: -0.0000

Data Index: 1685670 (The Pile)

Max Activating Token Index: 781

Text #14

Max Range: 0.6643. Min Range: -0.6643

Max Act: 0.5407. Min Act: -0.0000

Data Index: 151290 (The Pile)

Max Activating Token Index: 916

Text #15

Max Range: 0.6643. Min Range: -0.6643

Max Act: 0.4972. Min Act: -0.0000

Data Index: 581617 (The Pile)

Max Activating Token Index: 499

Text #16

Max Range: 0.6643. Min Range: -0.6643

Max Act: 0.5194. Min Act: -0.0000

Data Index: 1084918 (The Pile)

Max Activating Token Index: 889

Text #17

Max Range: 0.6643. Min Range: -0.6643

Max Act: 0.5052. Min Act: -0.0000

Data Index: 1171121 (The Pile)

Max Activating Token Index: 28

Text #18

Max Range: 0.6643. Min Range: -0.6643

Max Act: 0.5176. Min Act: -0.0000

Data Index: 188123 (The Pile)

Max Activating Token Index: 532

Text #19

Max Range: 0.6643. Min Range: -0.6643

Max Act: 0.5036. Min Act: -0.0000

Data Index: 1922294 (The Pile)

Max Activating Token Index: 857