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

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

Neuron 161 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4616. Min Range: -3.4616

Max Act: 3.4616. Min Act: -0.0000

Data Index: 1277691 (C4 (Web Text))

Max Activating Token Index: 159

Text #1

Max Range: 3.4616. Min Range: -3.4616

Max Act: 3.1184. Min Act: -0.0000

Data Index: 475908 (C4 (Web Text))

Max Activating Token Index: 506

Text #2

Max Range: 3.4616. Min Range: -3.4616

Max Act: 2.9772. Min Act: -0.0000

Data Index: 1438766 (Python Code)

Max Activating Token Index: 797

Text #3

Max Range: 3.4616. Min Range: -3.4616

Max Act: 2.6996. Min Act: -0.0000

Data Index: 298165 (C4 (Web Text))

Max Activating Token Index: 141

Text #4

Max Range: 3.4616. Min Range: -3.4616

Max Act: 2.8340. Min Act: -0.0000

Data Index: 1249928 (C4 (Web Text))

Max Activating Token Index: 261

Text #5

Max Range: 3.4616. Min Range: -3.4616

Max Act: 2.6940. Min Act: -0.0000

Data Index: 1231858 (C4 (Web Text))

Max Activating Token Index: 299

Text #6

Max Range: 3.4616. Min Range: -3.4616

Max Act: 2.4643. Min Act: 0.0000

Data Index: 87240 (C4 (Web Text))

Max Activating Token Index: 216

Text #7

Max Range: 3.4616. Min Range: -3.4616

Max Act: 2.5427. Min Act: -0.0000

Data Index: 156508 (C4 (Web Text))

Max Activating Token Index: 391

Text #8

Max Range: 3.4616. Min Range: -3.4616

Max Act: 2.5410. Min Act: 0.0000

Data Index: 1352927 (C4 (Web Text))

Max Activating Token Index: 306

Text #9

Max Range: 3.4616. Min Range: -3.4616

Max Act: 2.2841. Min Act: 0.0000

Data Index: 642295 (C4 (Web Text))

Max Activating Token Index: 61

Text #10

Max Range: 3.4616. Min Range: -3.4616

Max Act: 2.3055. Min Act: -0.0000

Data Index: 783558 (C4 (Web Text))

Max Activating Token Index: 925

Text #11

Max Range: 3.4616. Min Range: -3.4616

Max Act: 2.1604. Min Act: -0.0000

Data Index: 486756 (C4 (Web Text))

Max Activating Token Index: 341

Text #12

Max Range: 3.4616. Min Range: -3.4616

Max Act: 2.0597. Min Act: -0.0000

Data Index: 724567 (C4 (Web Text))

Max Activating Token Index: 457

Text #13

Max Range: 3.4616. Min Range: -3.4616

Max Act: 2.1644. Min Act: -0.0000

Data Index: 1068754 (C4 (Web Text))

Max Activating Token Index: 325

Text #14

Max Range: 3.4616. Min Range: -3.4616

Max Act: 2.1342. Min Act: -0.0000

Data Index: 1339478 (C4 (Web Text))

Max Activating Token Index: 718

Text #15

Max Range: 3.4616. Min Range: -3.4616

Max Act: 2.2490. Min Act: -0.0000

Data Index: 106571 (C4 (Web Text))

Max Activating Token Index: 647

Text #16

Max Range: 3.4616. Min Range: -3.4616

Max Act: 2.2292. Min Act: 0.0000

Data Index: 855622 (C4 (Web Text))

Max Activating Token Index: 173

Text #17

Max Range: 3.4616. Min Range: -3.4616

Max Act: 2.1085. Min Act: 0.0000

Data Index: 145446 (C4 (Web Text))

Max Activating Token Index: 564

Text #18

Max Range: 3.4616. Min Range: -3.4616

Max Act: 2.1021. Min Act: -0.0000

Data Index: 169791 (C4 (Web Text))

Max Activating Token Index: 59

Text #19

Max Range: 3.4616. Min Range: -3.4616

Max Act: 2.1904. Min Act: 0.0000

Data Index: 552387 (C4 (Web Text))

Max Activating Token Index: 41