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

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

Neuron 226 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5683. Min Range: -2.5683

Max Act: 2.5683. Min Act: -0.0000

Data Index: 1133115 (C4 (Web Text))

Max Activating Token Index: 748

Text #1

Max Range: 2.5683. Min Range: -2.5683

Max Act: 2.3797. Min Act: -0.0000

Data Index: 1149813 (C4 (Web Text))

Max Activating Token Index: 576

Text #2

Max Range: 2.5683. Min Range: -2.5683

Max Act: 2.3106. Min Act: -0.0000

Data Index: 704051 (C4 (Web Text))

Max Activating Token Index: 143

Text #3

Max Range: 2.5683. Min Range: -2.5683

Max Act: 2.0989. Min Act: -0.0000

Data Index: 575716 (C4 (Web Text))

Max Activating Token Index: 379

Text #4

Max Range: 2.5683. Min Range: -2.5683

Max Act: 2.0680. Min Act: -0.0000

Data Index: 483883 (C4 (Web Text))

Max Activating Token Index: 422

Text #5

Max Range: 2.5683. Min Range: -2.5683

Max Act: 2.0526. Min Act: -0.0000

Data Index: 619494 (C4 (Web Text))

Max Activating Token Index: 484

Text #6

Max Range: 2.5683. Min Range: -2.5683

Max Act: 1.9919. Min Act: -0.0000

Data Index: 1083323 (C4 (Web Text))

Max Activating Token Index: 587

Text #7

Max Range: 2.5683. Min Range: -2.5683

Max Act: 2.1011. Min Act: -0.0000

Data Index: 790513 (C4 (Web Text))

Max Activating Token Index: 309

Text #8

Max Range: 2.5683. Min Range: -2.5683

Max Act: 1.8377. Min Act: -0.0000

Data Index: 102105 (C4 (Web Text))

Max Activating Token Index: 224

Text #9

Max Range: 2.5683. Min Range: -2.5683

Max Act: 1.9246. Min Act: -0.0000

Data Index: 1329556 (C4 (Web Text))

Max Activating Token Index: 202

Text #10

Max Range: 2.5683. Min Range: -2.5683

Max Act: 1.8219. Min Act: -0.0000

Data Index: 515783 (C4 (Web Text))

Max Activating Token Index: 36

Text #11

Max Range: 2.5683. Min Range: -2.5683

Max Act: 1.8912. Min Act: -0.0000

Data Index: 537449 (C4 (Web Text))

Max Activating Token Index: 880

Text #12

Max Range: 2.5683. Min Range: -2.5683

Max Act: 1.8969. Min Act: -0.0000

Data Index: 571134 (C4 (Web Text))

Max Activating Token Index: 285

Text #13

Max Range: 2.5683. Min Range: -2.5683

Max Act: 1.7524. Min Act: -0.0000

Data Index: 822140 (C4 (Web Text))

Max Activating Token Index: 78

Text #14

Max Range: 2.5683. Min Range: -2.5683

Max Act: 1.9416. Min Act: -0.0000

Data Index: 962389 (C4 (Web Text))

Max Activating Token Index: 26

Text #15

Max Range: 2.5683. Min Range: -2.5683

Max Act: 1.9279. Min Act: -0.0000

Data Index: 1278654 (C4 (Web Text))

Max Activating Token Index: 639

Text #16

Max Range: 2.5683. Min Range: -2.5683

Max Act: 1.8158. Min Act: -0.0000

Data Index: 197876 (C4 (Web Text))

Max Activating Token Index: 204

Text #17

Max Range: 2.5683. Min Range: -2.5683

Max Act: 1.8091. Min Act: -0.0000

Data Index: 827416 (C4 (Web Text))

Max Activating Token Index: 757

Text #18

Max Range: 2.5683. Min Range: -2.5683

Max Act: 1.9025. Min Act: -0.0000

Data Index: 1121576 (C4 (Web Text))

Max Activating Token Index: 488

Text #19

Max Range: 2.5683. Min Range: -2.5683

Max Act: 1.7969. Min Act: -0.0000

Data Index: 188456 (C4 (Web Text))

Max Activating Token Index: 625