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

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

Neuron 4042 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: 2.3535. Min Range: -2.3535

Max Act: 2.3535. Min Act: -0.0002

Data Index: 685727 (C4 (Web Text))

Max Activating Token Index: 615

Text #1

Max Range: 2.3535. Min Range: -2.3535

Max Act: 2.1726. Min Act: -0.0002

Data Index: 497854 (C4 (Web Text))

Max Activating Token Index: 685

Text #2

Max Range: 2.3535. Min Range: -2.3535

Max Act: 2.0354. Min Act: -0.0002

Data Index: 537430 (C4 (Web Text))

Max Activating Token Index: 879

Text #3

Max Range: 2.3535. Min Range: -2.3535

Max Act: 1.9256. Min Act: -0.0002

Data Index: 1353866 (C4 (Web Text))

Max Activating Token Index: 139

Text #4

Max Range: 2.3535. Min Range: -2.3535

Max Act: 1.8851. Min Act: -0.0002

Data Index: 50603 (C4 (Web Text))

Max Activating Token Index: 465

Text #5

Max Range: 2.3535. Min Range: -2.3535

Max Act: 1.8624. Min Act: -0.0002

Data Index: 97534 (C4 (Web Text))

Max Activating Token Index: 586

Text #6

Max Range: 2.3535. Min Range: -2.3535

Max Act: 1.9200. Min Act: -0.0002

Data Index: 1235027 (C4 (Web Text))

Max Activating Token Index: 141

Text #7

Max Range: 2.3535. Min Range: -2.3535

Max Act: 1.8820. Min Act: -0.0002

Data Index: 1307762 (C4 (Web Text))

Max Activating Token Index: 701

Text #8

Max Range: 2.3535. Min Range: -2.3535

Max Act: 1.8599. Min Act: -0.0002

Data Index: 1195132 (C4 (Web Text))

Max Activating Token Index: 684

Text #9

Max Range: 2.3535. Min Range: -2.3535

Max Act: 1.7497. Min Act: -0.0002

Data Index: 910451 (C4 (Web Text))

Max Activating Token Index: 293

Text #10

Max Range: 2.3535. Min Range: -2.3535

Max Act: 1.7612. Min Act: -0.0002

Data Index: 1043853 (C4 (Web Text))

Max Activating Token Index: 447

Text #11

Max Range: 2.3535. Min Range: -2.3535

Max Act: 1.7676. Min Act: -0.0002

Data Index: 1309866 (C4 (Web Text))

Max Activating Token Index: 543

Text #12

Max Range: 2.3535. Min Range: -2.3535

Max Act: 1.7306. Min Act: -0.0002

Data Index: 386063 (C4 (Web Text))

Max Activating Token Index: 661

Text #13

Max Range: 2.3535. Min Range: -2.3535

Max Act: 1.7359. Min Act: -0.0002

Data Index: 585544 (C4 (Web Text))

Max Activating Token Index: 620

Text #14

Max Range: 2.3535. Min Range: -2.3535

Max Act: 1.7858. Min Act: -0.0002

Data Index: 313734 (C4 (Web Text))

Max Activating Token Index: 660

Text #15

Max Range: 2.3535. Min Range: -2.3535

Max Act: 1.7192. Min Act: -0.0002

Data Index: 493526 (C4 (Web Text))

Max Activating Token Index: 896

Text #16

Max Range: 2.3535. Min Range: -2.3535

Max Act: 1.7597. Min Act: -0.0002

Data Index: 1139857 (C4 (Web Text))

Max Activating Token Index: 122

Text #17

Max Range: 2.3535. Min Range: -2.3535

Max Act: 1.7811. Min Act: -0.0002

Data Index: 823716 (C4 (Web Text))

Max Activating Token Index: 49

Text #18

Max Range: 2.3535. Min Range: -2.3535

Max Act: 1.7862. Min Act: -0.0002

Data Index: 1107169 (C4 (Web Text))

Max Activating Token Index: 584

Text #19

Max Range: 2.3535. Min Range: -2.3535

Max Act: 1.7430. Min Act: -0.0002

Data Index: 979647 (C4 (Web Text))

Max Activating Token Index: 356