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

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

Neuron 5648 in Layer 1

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: 1.6030. Min Range: -1.6030

Max Act: 1.6030. Min Act: -0.0002

Data Index: 806647 (C4 (Web Text))

Max Activating Token Index: 113

Text #1

Max Range: 1.6030. Min Range: -1.6030

Max Act: 1.5250. Min Act: -0.0002

Data Index: 867381 (C4 (Web Text))

Max Activating Token Index: 78

Text #2

Max Range: 1.6030. Min Range: -1.6030

Max Act: 1.4513. Min Act: -0.0002

Data Index: 240920 (C4 (Web Text))

Max Activating Token Index: 253

Text #3

Max Range: 1.6030. Min Range: -1.6030

Max Act: 1.4552. Min Act: -0.0002

Data Index: 624199 (C4 (Web Text))

Max Activating Token Index: 33

Text #4

Max Range: 1.6030. Min Range: -1.6030

Max Act: 1.3803. Min Act: -0.0002

Data Index: 1216077 (C4 (Web Text))

Max Activating Token Index: 529

Text #5

Max Range: 1.6030. Min Range: -1.6030

Max Act: 1.3758. Min Act: -0.0002

Data Index: 1055419 (C4 (Web Text))

Max Activating Token Index: 724

Text #6

Max Range: 1.6030. Min Range: -1.6030

Max Act: 1.3768. Min Act: -0.0002

Data Index: 219665 (C4 (Web Text))

Max Activating Token Index: 775

Text #7

Max Range: 1.6030. Min Range: -1.6030

Max Act: 1.3003. Min Act: -0.0002

Data Index: 274965 (C4 (Web Text))

Max Activating Token Index: 107

Text #8

Max Range: 1.6030. Min Range: -1.6030

Max Act: 1.2646. Min Act: -0.0002

Data Index: 776877 (C4 (Web Text))

Max Activating Token Index: 667

Text #9

Max Range: 1.6030. Min Range: -1.6030

Max Act: 1.2904. Min Act: -0.0002

Data Index: 1089328 (C4 (Web Text))

Max Activating Token Index: 151

Text #10

Max Range: 1.6030. Min Range: -1.6030

Max Act: 1.2531. Min Act: -0.0002

Data Index: 304011 (C4 (Web Text))

Max Activating Token Index: 473

Text #11

Max Range: 1.6030. Min Range: -1.6030

Max Act: 1.2620. Min Act: -0.0002

Data Index: 180563 (C4 (Web Text))

Max Activating Token Index: 716

Text #12

Max Range: 1.6030. Min Range: -1.6030

Max Act: 1.2370. Min Act: -0.0002

Data Index: 1113729 (C4 (Web Text))

Max Activating Token Index: 134

Text #13

Max Range: 1.6030. Min Range: -1.6030

Max Act: 1.2078. Min Act: -0.0002

Data Index: 698188 (C4 (Web Text))

Max Activating Token Index: 29

Text #14

Max Range: 1.6030. Min Range: -1.6030

Max Act: 1.2252. Min Act: -0.0002

Data Index: 200336 (C4 (Web Text))

Max Activating Token Index: 21

Text #15

Max Range: 1.6030. Min Range: -1.6030

Max Act: 1.1902. Min Act: -0.0002

Data Index: 530021 (C4 (Web Text))

Max Activating Token Index: 834

Text #16

Max Range: 1.6030. Min Range: -1.6030

Max Act: 1.1741. Min Act: -0.0002

Data Index: 219501 (C4 (Web Text))

Max Activating Token Index: 692

Text #17

Max Range: 1.6030. Min Range: -1.6030

Max Act: 1.1894. Min Act: -0.0002

Data Index: 540643 (C4 (Web Text))

Max Activating Token Index: 493

Text #18

Max Range: 1.6030. Min Range: -1.6030

Max Act: 1.1655. Min Act: -0.0002

Data Index: 555587 (C4 (Web Text))

Max Activating Token Index: 353

Text #19

Max Range: 1.6030. Min Range: -1.6030

Max Act: 1.1627. Min Act: -0.0002

Data Index: 447756 (C4 (Web Text))

Max Activating Token Index: 128