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

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

Neuron 3156 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: 0.0870. Min Range: -0.0870

Max Act: 0.0870. Min Act: -0.0001

Data Index: 952608 (C4 (Web Text))

Max Activating Token Index: 552

Text #1

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0863. Min Act: -0.0001

Data Index: 614172 (C4 (Web Text))

Max Activating Token Index: 4

Text #2

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0776. Min Act: -0.0001

Data Index: 286951 (C4 (Web Text))

Max Activating Token Index: 248

Text #3

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0777. Min Act: -0.0001

Data Index: 523822 (C4 (Web Text))

Max Activating Token Index: 287

Text #4

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0736. Min Act: -0.0001

Data Index: 921494 (C4 (Web Text))

Max Activating Token Index: 74

Text #5

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0719. Min Act: -0.0001

Data Index: 769244 (C4 (Web Text))

Max Activating Token Index: 35

Text #6

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0727. Min Act: -0.0001

Data Index: 327947 (C4 (Web Text))

Max Activating Token Index: 103

Text #7

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0734. Min Act: -0.0001

Data Index: 274531 (C4 (Web Text))

Max Activating Token Index: 240

Text #8

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0719. Min Act: -0.0001

Data Index: 750011 (C4 (Web Text))

Max Activating Token Index: 629

Text #9

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0692. Min Act: -0.0001

Data Index: 181296 (C4 (Web Text))

Max Activating Token Index: 50

Text #10

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0679. Min Act: -0.0001

Data Index: 724948 (C4 (Web Text))

Max Activating Token Index: 535

Text #11

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0673. Min Act: -0.0001

Data Index: 1355551 (C4 (Web Text))

Max Activating Token Index: 56

Text #12

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0658. Min Act: -0.0001

Data Index: 1047806 (C4 (Web Text))

Max Activating Token Index: 194

Text #13

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0638. Min Act: -0.0001

Data Index: 1047600 (C4 (Web Text))

Max Activating Token Index: 395

Text #14

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0636. Min Act: -0.0001

Data Index: 373283 (C4 (Web Text))

Max Activating Token Index: 730

Text #15

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0646. Min Act: -0.0001

Data Index: 1120458 (C4 (Web Text))

Max Activating Token Index: 669

Text #16

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0622. Min Act: -0.0001

Data Index: 1272986 (C4 (Web Text))

Max Activating Token Index: 802

Text #17

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0632. Min Act: -0.0001

Data Index: 551733 (C4 (Web Text))

Max Activating Token Index: 111

Text #18

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0632. Min Act: -0.0001

Data Index: 819984 (C4 (Web Text))

Max Activating Token Index: 1009

Text #19

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0638. Min Act: -0.0001

Data Index: 1237523 (C4 (Web Text))

Max Activating Token Index: 779