Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1532 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.8711. Min Range: -0.8711

Max Act: 0.8561. Min Act: -0.0000

Data Index: 569414 (C4 (Web Text))

Max Activating Token Index: 901

Text #1

Max Range: 0.8711. Min Range: -0.8711

Max Act: 0.8698. Min Act: -0.0000

Data Index: 10423 (C4 (Web Text))

Max Activating Token Index: 115

Text #2

Max Range: 0.8711. Min Range: -0.8711

Max Act: 0.8615. Min Act: -0.0000

Data Index: 486761 (C4 (Web Text))

Max Activating Token Index: 84

Text #3

Max Range: 0.8711. Min Range: -0.8711

Max Act: 0.8711. Min Act: -0.0000

Data Index: 1080584 (C4 (Web Text))

Max Activating Token Index: 146

Text #4

Max Range: 0.8711. Min Range: -0.8711

Max Act: 0.7689. Min Act: -0.0000

Data Index: 535343 (C4 (Web Text))

Max Activating Token Index: 814

Text #5

Max Range: 0.8711. Min Range: -0.8711

Max Act: 0.7395. Min Act: 0.0000

Data Index: 1082122 (C4 (Web Text))

Max Activating Token Index: 135

Text #6

Max Range: 0.8711. Min Range: -0.8711

Max Act: 0.7345. Min Act: -0.0000

Data Index: 892770 (C4 (Web Text))

Max Activating Token Index: 109

Text #7

Max Range: 0.8711. Min Range: -0.8711

Max Act: 0.7301. Min Act: -0.0000

Data Index: 1039631 (C4 (Web Text))

Max Activating Token Index: 829

Text #8

Max Range: 0.8711. Min Range: -0.8711

Max Act: 0.7339. Min Act: -0.0000

Data Index: 5918 (C4 (Web Text))

Max Activating Token Index: 535

Text #9

Max Range: 0.8711. Min Range: -0.8711

Max Act: 0.7438. Min Act: -0.0000

Data Index: 1161450 (C4 (Web Text))

Max Activating Token Index: 706

Text #10

Max Range: 0.8711. Min Range: -0.8711

Max Act: 0.7378. Min Act: -0.0000

Data Index: 1313939 (C4 (Web Text))

Max Activating Token Index: 349

Text #11

Max Range: 0.8711. Min Range: -0.8711

Max Act: 0.6951. Min Act: -0.0000

Data Index: 465070 (C4 (Web Text))

Max Activating Token Index: 94

Text #12

Max Range: 0.8711. Min Range: -0.8711

Max Act: 0.7117. Min Act: -0.0000

Data Index: 1129042 (C4 (Web Text))

Max Activating Token Index: 159

Text #13

Max Range: 0.8711. Min Range: -0.8711

Max Act: 0.7112. Min Act: -0.0000

Data Index: 1168983 (C4 (Web Text))

Max Activating Token Index: 705

Text #14

Max Range: 0.8711. Min Range: -0.8711

Max Act: 0.6852. Min Act: -0.0000

Data Index: 939632 (C4 (Web Text))

Max Activating Token Index: 485

Text #15

Max Range: 0.8711. Min Range: -0.8711

Max Act: 0.6993. Min Act: -0.0000

Data Index: 797776 (C4 (Web Text))

Max Activating Token Index: 311

Text #16

Max Range: 0.8711. Min Range: -0.8711

Max Act: 0.6743. Min Act: -0.0000

Data Index: 1173690 (C4 (Web Text))

Max Activating Token Index: 576

Text #17

Max Range: 0.8711. Min Range: -0.8711

Max Act: 0.6918. Min Act: -0.0000

Data Index: 1143323 (C4 (Web Text))

Max Activating Token Index: 267

Text #18

Max Range: 0.8711. Min Range: -0.8711

Max Act: 0.6885. Min Act: -0.0000

Data Index: 726308 (C4 (Web Text))

Max Activating Token Index: 742

Text #19

Max Range: 0.8711. Min Range: -0.8711

Max Act: 0.6908. Min Act: -0.0000

Data Index: 1250355 (C4 (Web Text))

Max Activating Token Index: 709