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

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

Neuron 5728 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.5188. Min Range: -0.5188

Max Act: 0.5188. Min Act: -0.0001

Data Index: 1330082 (C4 (Web Text))

Max Activating Token Index: 149

Text #1

Max Range: 0.5188. Min Range: -0.5188

Max Act: 0.4912. Min Act: -0.0001

Data Index: 550761 (C4 (Web Text))

Max Activating Token Index: 56

Text #2

Max Range: 0.5188. Min Range: -0.5188

Max Act: 0.4464. Min Act: -0.0001

Data Index: 672602 (C4 (Web Text))

Max Activating Token Index: 78

Text #3

Max Range: 0.5188. Min Range: -0.5188

Max Act: 0.4400. Min Act: -0.0001

Data Index: 986338 (C4 (Web Text))

Max Activating Token Index: 110

Text #4

Max Range: 0.5188. Min Range: -0.5188

Max Act: 0.4355. Min Act: -0.0001

Data Index: 1099843 (C4 (Web Text))

Max Activating Token Index: 231

Text #5

Max Range: 0.5188. Min Range: -0.5188

Max Act: 0.4213. Min Act: -0.0001

Data Index: 494348 (C4 (Web Text))

Max Activating Token Index: 110

Text #6

Max Range: 0.5188. Min Range: -0.5188

Max Act: 0.4259. Min Act: -0.0001

Data Index: 773473 (C4 (Web Text))

Max Activating Token Index: 321

Text #7

Max Range: 0.5188. Min Range: -0.5188

Max Act: 0.4023. Min Act: -0.0001

Data Index: 873751 (C4 (Web Text))

Max Activating Token Index: 851

Text #8

Max Range: 0.5188. Min Range: -0.5188

Max Act: 0.3986. Min Act: -0.0001

Data Index: 733715 (C4 (Web Text))

Max Activating Token Index: 67

Text #9

Max Range: 0.5188. Min Range: -0.5188

Max Act: 0.3761. Min Act: -0.0001

Data Index: 655904 (C4 (Web Text))

Max Activating Token Index: 456

Text #10

Max Range: 0.5188. Min Range: -0.5188

Max Act: 0.3782. Min Act: -0.0001

Data Index: 934226 (C4 (Web Text))

Max Activating Token Index: 297

Text #11

Max Range: 0.5188. Min Range: -0.5188

Max Act: 0.3732. Min Act: -0.0001

Data Index: 90018 (C4 (Web Text))

Max Activating Token Index: 86

Text #12

Max Range: 0.5188. Min Range: -0.5188

Max Act: 0.3658. Min Act: -0.0002

Data Index: 558943 (C4 (Web Text))

Max Activating Token Index: 481

Text #13

Max Range: 0.5188. Min Range: -0.5188

Max Act: 0.3612. Min Act: -0.0001

Data Index: 122422 (C4 (Web Text))

Max Activating Token Index: 951

Text #14

Max Range: 0.5188. Min Range: -0.5188

Max Act: 0.3536. Min Act: -0.0001

Data Index: 958040 (C4 (Web Text))

Max Activating Token Index: 224

Text #15

Max Range: 0.5188. Min Range: -0.5188

Max Act: 0.3536. Min Act: -0.0001

Data Index: 1196107 (C4 (Web Text))

Max Activating Token Index: 168

Text #16

Max Range: 0.5188. Min Range: -0.5188

Max Act: 0.3408. Min Act: -0.0001

Data Index: 798801 (C4 (Web Text))

Max Activating Token Index: 741

Text #17

Max Range: 0.5188. Min Range: -0.5188

Max Act: 0.3445. Min Act: -0.0001

Data Index: 177075 (C4 (Web Text))

Max Activating Token Index: 812

Text #18

Max Range: 0.5188. Min Range: -0.5188

Max Act: 0.3373. Min Act: -0.0001

Data Index: 1178548 (C4 (Web Text))

Max Activating Token Index: 172

Text #19

Max Range: 0.5188. Min Range: -0.5188

Max Act: 0.3329. Min Act: -0.0001

Data Index: 224932 (C4 (Web Text))

Max Activating Token Index: 882