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

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

Neuron 339 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7126. Min Range: -0.7126

Max Act: 0.7126. Min Act: -0.0000

Data Index: 1078524 (C4 (Web Text))

Max Activating Token Index: 604

Text #1

Max Range: 0.7126. Min Range: -0.7126

Max Act: 0.6955. Min Act: -0.0000

Data Index: 1035657 (C4 (Web Text))

Max Activating Token Index: 493

Text #2

Max Range: 0.7126. Min Range: -0.7126

Max Act: 0.6457. Min Act: -0.0000

Data Index: 411327 (C4 (Web Text))

Max Activating Token Index: 624

Text #3

Max Range: 0.7126. Min Range: -0.7126

Max Act: 0.6546. Min Act: -0.0000

Data Index: 688523 (C4 (Web Text))

Max Activating Token Index: 375

Text #4

Max Range: 0.7126. Min Range: -0.7126

Max Act: 0.6376. Min Act: -0.0000

Data Index: 859143 (C4 (Web Text))

Max Activating Token Index: 432

Text #5

Max Range: 0.7126. Min Range: -0.7126

Max Act: 0.6405. Min Act: -0.0000

Data Index: 354761 (C4 (Web Text))

Max Activating Token Index: 291

Text #6

Max Range: 0.7126. Min Range: -0.7126

Max Act: 0.6431. Min Act: -0.0000

Data Index: 1306371 (C4 (Web Text))

Max Activating Token Index: 441

Text #7

Max Range: 0.7126. Min Range: -0.7126

Max Act: 0.6101. Min Act: -0.0000

Data Index: 14957 (C4 (Web Text))

Max Activating Token Index: 761

Text #8

Max Range: 0.7126. Min Range: -0.7126

Max Act: 0.5853. Min Act: -0.0000

Data Index: 440749 (C4 (Web Text))

Max Activating Token Index: 152

Text #9

Max Range: 0.7126. Min Range: -0.7126

Max Act: 0.4977. Min Act: -0.0000

Data Index: 183092 (C4 (Web Text))

Max Activating Token Index: 625

Text #10

Max Range: 0.7126. Min Range: -0.7126

Max Act: 0.4351. Min Act: -0.0000

Data Index: 1160911 (C4 (Web Text))

Max Activating Token Index: 783

Text #11

Max Range: 0.7126. Min Range: -0.7126

Max Act: 0.4671. Min Act: -0.0000

Data Index: 193697 (C4 (Web Text))

Max Activating Token Index: 850

Text #12

Max Range: 0.7126. Min Range: -0.7126

Max Act: 0.4614. Min Act: -0.0000

Data Index: 687679 (C4 (Web Text))

Max Activating Token Index: 609

Text #13

Max Range: 0.7126. Min Range: -0.7126

Max Act: 0.4068. Min Act: -0.0000

Data Index: 616394 (C4 (Web Text))

Max Activating Token Index: 804

Text #14

Max Range: 0.7126. Min Range: -0.7126

Max Act: 0.4010. Min Act: -0.0000

Data Index: 717520 (C4 (Web Text))

Max Activating Token Index: 118

Text #15

Max Range: 0.7126. Min Range: -0.7126

Max Act: 0.4198. Min Act: -0.0000

Data Index: 484097 (C4 (Web Text))

Max Activating Token Index: 543

Text #16

Max Range: 0.7126. Min Range: -0.7126

Max Act: 0.3540. Min Act: -0.0000

Data Index: 1072555 (C4 (Web Text))

Max Activating Token Index: 466

Text #17

Max Range: 0.7126. Min Range: -0.7126

Max Act: 0.3554. Min Act: -0.0000

Data Index: 840691 (C4 (Web Text))

Max Activating Token Index: 899

Text #18

Max Range: 0.7126. Min Range: -0.7126

Max Act: 0.3672. Min Act: -0.0000

Data Index: 757992 (C4 (Web Text))

Max Activating Token Index: 856

Text #19

Max Range: 0.7126. Min Range: -0.7126

Max Act: 0.3863. Min Act: -0.0000

Data Index: 1148556 (C4 (Web Text))

Max Activating Token Index: 301