Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2655 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0501. Min Act: -0.0001

Data Index: 1355995 (C4 (Web Text))

Max Activating Token Index: 1004

Text #1

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0498. Min Act: -0.0001

Data Index: 75225 (C4 (Web Text))

Max Activating Token Index: 727

Text #2

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0505. Min Act: -0.0001

Data Index: 407062 (C4 (Web Text))

Max Activating Token Index: 102

Text #3

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0490. Min Act: -0.0001

Data Index: 316048 (C4 (Web Text))

Max Activating Token Index: 258

Text #4

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0479. Min Act: -0.0001

Data Index: 435748 (C4 (Web Text))

Max Activating Token Index: 841

Text #5

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0499. Min Act: -0.0001

Data Index: 1240135 (C4 (Web Text))

Max Activating Token Index: 206

Text #6

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0468. Min Act: -0.0001

Data Index: 1259400 (C4 (Web Text))

Max Activating Token Index: 404

Text #7

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0462. Min Act: -0.0001

Data Index: 602866 (C4 (Web Text))

Max Activating Token Index: 200

Text #8

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0435. Min Act: -0.0001

Data Index: 288113 (C4 (Web Text))

Max Activating Token Index: 931

Text #9

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0483. Min Act: -0.0001

Data Index: 1328018 (C4 (Web Text))

Max Activating Token Index: 355

Text #10

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0456. Min Act: -0.0001

Data Index: 753732 (C4 (Web Text))

Max Activating Token Index: 865

Text #11

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0445. Min Act: -0.0001

Data Index: 694861 (C4 (Web Text))

Max Activating Token Index: 534

Text #12

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0433. Min Act: -0.0001

Data Index: 1133799 (C4 (Web Text))

Max Activating Token Index: 811

Text #13

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0481. Min Act: -0.0001

Data Index: 906795 (C4 (Web Text))

Max Activating Token Index: 265

Text #14

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0435. Min Act: -0.0001

Data Index: 744179 (C4 (Web Text))

Max Activating Token Index: 867

Text #15

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0421. Min Act: -0.0001

Data Index: 792194 (C4 (Web Text))

Max Activating Token Index: 531

Text #16

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0441. Min Act: -0.0001

Data Index: 867605 (C4 (Web Text))

Max Activating Token Index: 701

Text #17

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0417. Min Act: -0.0001

Data Index: 1098756 (C4 (Web Text))

Max Activating Token Index: 593

Text #18

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0420. Min Act: -0.0001

Data Index: 35168 (C4 (Web Text))

Max Activating Token Index: 546

Text #19

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0398. Min Act: -0.0001

Data Index: 1125628 (C4 (Web Text))

Max Activating Token Index: 1004