Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3164 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.5522. Min Range: -2.5522

Max Act: 2.5522. Min Act: -0.0000

Data Index: 543042 (C4 (Web Text))

Max Activating Token Index: 275

Text #1

Max Range: 2.5522. Min Range: -2.5522

Max Act: 2.3932. Min Act: -0.0000

Data Index: 867866 (C4 (Web Text))

Max Activating Token Index: 157

Text #2

Max Range: 2.5522. Min Range: -2.5522

Max Act: 2.3353. Min Act: -0.0000

Data Index: 598266 (C4 (Web Text))

Max Activating Token Index: 451

Text #3

Max Range: 2.5522. Min Range: -2.5522

Max Act: 2.3032. Min Act: -0.0000

Data Index: 782948 (C4 (Web Text))

Max Activating Token Index: 553

Text #4

Max Range: 2.5522. Min Range: -2.5522

Max Act: 2.2704. Min Act: -0.0000

Data Index: 147436 (C4 (Web Text))

Max Activating Token Index: 601

Text #5

Max Range: 2.5522. Min Range: -2.5522

Max Act: 2.0488. Min Act: -0.0000

Data Index: 583166 (C4 (Web Text))

Max Activating Token Index: 912

Text #6

Max Range: 2.5522. Min Range: -2.5522

Max Act: 2.2520. Min Act: -0.0000

Data Index: 1216182 (C4 (Web Text))

Max Activating Token Index: 323

Text #7

Max Range: 2.5522. Min Range: -2.5522

Max Act: 2.2173. Min Act: -0.0000

Data Index: 832572 (C4 (Web Text))

Max Activating Token Index: 526

Text #8

Max Range: 2.5522. Min Range: -2.5522

Max Act: 2.0973. Min Act: -0.0000

Data Index: 549451 (C4 (Web Text))

Max Activating Token Index: 922

Text #9

Max Range: 2.5522. Min Range: -2.5522

Max Act: 2.1695. Min Act: -0.0000

Data Index: 1023987 (C4 (Web Text))

Max Activating Token Index: 21

Text #10

Max Range: 2.5522. Min Range: -2.5522

Max Act: 2.1545. Min Act: -0.0000

Data Index: 973001 (C4 (Web Text))

Max Activating Token Index: 937

Text #11

Max Range: 2.5522. Min Range: -2.5522

Max Act: 2.1592. Min Act: -0.0000

Data Index: 744877 (C4 (Web Text))

Max Activating Token Index: 169

Text #12

Max Range: 2.5522. Min Range: -2.5522

Max Act: 2.0333. Min Act: -0.0000

Data Index: 160336 (C4 (Web Text))

Max Activating Token Index: 493

Text #13

Max Range: 2.5522. Min Range: -2.5522

Max Act: 2.0364. Min Act: -0.0000

Data Index: 1219059 (C4 (Web Text))

Max Activating Token Index: 126

Text #14

Max Range: 2.5522. Min Range: -2.5522

Max Act: 2.1331. Min Act: -0.0000

Data Index: 1012386 (C4 (Web Text))

Max Activating Token Index: 849

Text #15

Max Range: 2.5522. Min Range: -2.5522

Max Act: 2.0905. Min Act: -0.0000

Data Index: 737381 (C4 (Web Text))

Max Activating Token Index: 683

Text #16

Max Range: 2.5522. Min Range: -2.5522

Max Act: 2.1920. Min Act: -0.0000

Data Index: 1128740 (C4 (Web Text))

Max Activating Token Index: 119

Text #17

Max Range: 2.5522. Min Range: -2.5522

Max Act: 2.0697. Min Act: -0.0000

Data Index: 702351 (C4 (Web Text))

Max Activating Token Index: 732

Text #18

Max Range: 2.5522. Min Range: -2.5522

Max Act: 1.9501. Min Act: -0.0000

Data Index: 917401 (C4 (Web Text))

Max Activating Token Index: 234

Text #19

Max Range: 2.5522. Min Range: -2.5522

Max Act: 2.0520. Min Act: -0.0000

Data Index: 917582 (C4 (Web Text))

Max Activating Token Index: 968