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

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

Neuron 4779 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: 0.9561. Min Range: -0.9561

Max Act: 0.9561. Min Act: -0.0001

Data Index: 101491 (C4 (Web Text))

Max Activating Token Index: 39

Text #1

Max Range: 0.9561. Min Range: -0.9561

Max Act: 0.8975. Min Act: -0.0001

Data Index: 391002 (C4 (Web Text))

Max Activating Token Index: 147

Text #2

Max Range: 0.9561. Min Range: -0.9561

Max Act: 0.8871. Min Act: -0.0001

Data Index: 299059 (C4 (Web Text))

Max Activating Token Index: 58

Text #3

Max Range: 0.9561. Min Range: -0.9561

Max Act: 0.8920. Min Act: -0.0001

Data Index: 674996 (C4 (Web Text))

Max Activating Token Index: 418

Text #4

Max Range: 0.9561. Min Range: -0.9561

Max Act: 0.8874. Min Act: -0.0001

Data Index: 1137528 (C4 (Web Text))

Max Activating Token Index: 684

Text #5

Max Range: 0.9561. Min Range: -0.9561

Max Act: 0.8675. Min Act: -0.0001

Data Index: 117236 (C4 (Web Text))

Max Activating Token Index: 728

Text #6

Max Range: 0.9561. Min Range: -0.9561

Max Act: 0.8759. Min Act: -0.0001

Data Index: 768859 (C4 (Web Text))

Max Activating Token Index: 13

Text #7

Max Range: 0.9561. Min Range: -0.9561

Max Act: 0.8634. Min Act: -0.0001

Data Index: 317459 (C4 (Web Text))

Max Activating Token Index: 589

Text #8

Max Range: 0.9561. Min Range: -0.9561

Max Act: 0.8776. Min Act: -0.0001

Data Index: 28161 (C4 (Web Text))

Max Activating Token Index: 864

Text #9

Max Range: 0.9561. Min Range: -0.9561

Max Act: 0.8562. Min Act: -0.0001

Data Index: 515718 (C4 (Web Text))

Max Activating Token Index: 499

Text #10

Max Range: 0.9561. Min Range: -0.9561

Max Act: 0.8529. Min Act: -0.0001

Data Index: 235568 (C4 (Web Text))

Max Activating Token Index: 17

Text #11

Max Range: 0.9561. Min Range: -0.9561

Max Act: 0.8389. Min Act: -0.0001

Data Index: 1300831 (C4 (Web Text))

Max Activating Token Index: 81

Text #12

Max Range: 0.9561. Min Range: -0.9561

Max Act: 0.8225. Min Act: -0.0001

Data Index: 864579 (C4 (Web Text))

Max Activating Token Index: 835

Text #13

Max Range: 0.9561. Min Range: -0.9561

Max Act: 0.8447. Min Act: -0.0001

Data Index: 48546 (C4 (Web Text))

Max Activating Token Index: 802

Text #14

Max Range: 0.9561. Min Range: -0.9561

Max Act: 0.8567. Min Act: -0.0001

Data Index: 1143459 (C4 (Web Text))

Max Activating Token Index: 682

Text #15

Max Range: 0.9561. Min Range: -0.9561

Max Act: 0.8540. Min Act: -0.0001

Data Index: 780911 (C4 (Web Text))

Max Activating Token Index: 882

Text #16

Max Range: 0.9561. Min Range: -0.9561

Max Act: 0.8503. Min Act: -0.0001

Data Index: 737774 (C4 (Web Text))

Max Activating Token Index: 667

Text #17

Max Range: 0.9561. Min Range: -0.9561

Max Act: 0.8330. Min Act: -0.0001

Data Index: 1296104 (C4 (Web Text))

Max Activating Token Index: 420

Text #18

Max Range: 0.9561. Min Range: -0.9561

Max Act: 0.8326. Min Act: -0.0001

Data Index: 708747 (C4 (Web Text))

Max Activating Token Index: 412

Text #19

Max Range: 0.9561. Min Range: -0.9561

Max Act: 0.8207. Min Act: -0.0001

Data Index: 198206 (C4 (Web Text))

Max Activating Token Index: 838