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

Dataset: The Pile

Neuron 1532 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9043. Min Range: -0.9043

Max Act: 0.9043. Min Act: -0.0000

Data Index: 213551 (The Pile)

Max Activating Token Index: 51

Text #1

Max Range: 0.9043. Min Range: -0.9043

Max Act: 0.8594. Min Act: -0.0000

Data Index: 1906096 (The Pile)

Max Activating Token Index: 573

Text #2

Max Range: 0.9043. Min Range: -0.9043

Max Act: 0.8914. Min Act: -0.0000

Data Index: 794354 (The Pile)

Max Activating Token Index: 708

Text #3

Max Range: 0.9043. Min Range: -0.9043

Max Act: 0.8538. Min Act: -0.0000

Data Index: 1624972 (The Pile)

Max Activating Token Index: 935

Text #4

Max Range: 0.9043. Min Range: -0.9043

Max Act: 0.7931. Min Act: -0.0000

Data Index: 1105163 (The Pile)

Max Activating Token Index: 1001

Text #5

Max Range: 0.9043. Min Range: -0.9043

Max Act: 0.8213. Min Act: -0.0000

Data Index: 807818 (The Pile)

Max Activating Token Index: 456

Text #6

Max Range: 0.9043. Min Range: -0.9043

Max Act: 0.8373. Min Act: -0.0000

Data Index: 1018493 (The Pile)

Max Activating Token Index: 910

Text #7

Max Range: 0.9043. Min Range: -0.9043

Max Act: 0.7818. Min Act: -0.0000

Data Index: 39441 (The Pile)

Max Activating Token Index: 823

Text #8

Max Range: 0.9043. Min Range: -0.9043

Max Act: 0.7874. Min Act: -0.0000

Data Index: 592679 (The Pile)

Max Activating Token Index: 643

Text #9

Max Range: 0.9043. Min Range: -0.9043

Max Act: 0.6826. Min Act: -0.0000

Data Index: 728492 (The Pile)

Max Activating Token Index: 274

Text #10

Max Range: 0.9043. Min Range: -0.9043

Max Act: 0.6938. Min Act: -0.0000

Data Index: 470863 (The Pile)

Max Activating Token Index: 330

Text #11

Max Range: 0.9043. Min Range: -0.9043

Max Act: 0.6711. Min Act: 0.0000

Data Index: 282924 (The Pile)

Max Activating Token Index: 777

Text #12

Max Range: 0.9043. Min Range: -0.9043

Max Act: 0.7198. Min Act: -0.0000

Data Index: 644912 (The Pile)

Max Activating Token Index: 750

Text #13

Max Range: 0.9043. Min Range: -0.9043

Max Act: 0.6829. Min Act: -0.0000

Data Index: 415679 (The Pile)

Max Activating Token Index: 895

Text #14

Max Range: 0.9043. Min Range: -0.9043

Max Act: 0.6453. Min Act: -0.0000

Data Index: 1500501 (The Pile)

Max Activating Token Index: 201

Text #15

Max Range: 0.9043. Min Range: -0.9043

Max Act: 0.6677. Min Act: -0.0000

Data Index: 1242267 (The Pile)

Max Activating Token Index: 194

Text #16

Max Range: 0.9043. Min Range: -0.9043

Max Act: 0.6612. Min Act: -0.0000

Data Index: 1391880 (The Pile)

Max Activating Token Index: 202

Text #17

Max Range: 0.9043. Min Range: -0.9043

Max Act: 0.6029. Min Act: -0.0000

Data Index: 334168 (The Pile)

Max Activating Token Index: 989

Text #18

Max Range: 0.9043. Min Range: -0.9043

Max Act: 0.6530. Min Act: 0.0000

Data Index: 1259636 (The Pile)

Max Activating Token Index: 696

Text #19

Max Range: 0.9043. Min Range: -0.9043

Max Act: 0.6314. Min Act: -0.0000

Data Index: 261599 (The Pile)

Max Activating Token Index: 624