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

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

Neuron 5241 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 4.7737. Min Range: -4.7737

Max Act: 4.7737. Min Act: -0.0000

Data Index: 1116443 (C4 (Web Text))

Max Activating Token Index: 615

Text #1

Max Range: 4.7737. Min Range: -4.7737

Max Act: 4.2502. Min Act: -0.0000

Data Index: 754192 (C4 (Web Text))

Max Activating Token Index: 758

Text #2

Max Range: 4.7737. Min Range: -4.7737

Max Act: 3.9865. Min Act: -0.0000

Data Index: 668588 (C4 (Web Text))

Max Activating Token Index: 898

Text #3

Max Range: 4.7737. Min Range: -4.7737

Max Act: 3.5104. Min Act: -0.0000

Data Index: 25080 (C4 (Web Text))

Max Activating Token Index: 417

Text #4

Max Range: 4.7737. Min Range: -4.7737

Max Act: 3.3333. Min Act: -0.0000

Data Index: 408690 (C4 (Web Text))

Max Activating Token Index: 558

Text #5

Max Range: 4.7737. Min Range: -4.7737

Max Act: 3.3925. Min Act: -0.0000

Data Index: 1216522 (C4 (Web Text))

Max Activating Token Index: 479

Text #6

Max Range: 4.7737. Min Range: -4.7737

Max Act: 2.5541. Min Act: -0.0000

Data Index: 481074 (C4 (Web Text))

Max Activating Token Index: 612

Text #7

Max Range: 4.7737. Min Range: -4.7737

Max Act: 2.6545. Min Act: -0.0000

Data Index: 544877 (C4 (Web Text))

Max Activating Token Index: 374

Text #8

Max Range: 4.7737. Min Range: -4.7737

Max Act: 2.8260. Min Act: -0.0000

Data Index: 835288 (C4 (Web Text))

Max Activating Token Index: 516

Text #9

Max Range: 4.7737. Min Range: -4.7737

Max Act: 2.6635. Min Act: -0.0000

Data Index: 576504 (C4 (Web Text))

Max Activating Token Index: 657

Text #10

Max Range: 4.7737. Min Range: -4.7737

Max Act: 2.3976. Min Act: -0.0000

Data Index: 584938 (C4 (Web Text))

Max Activating Token Index: 891

Text #11

Max Range: 4.7737. Min Range: -4.7737

Max Act: 2.6395. Min Act: -0.0000

Data Index: 353195 (C4 (Web Text))

Max Activating Token Index: 184

Text #12

Max Range: 4.7737. Min Range: -4.7737

Max Act: 2.6461. Min Act: -0.0000

Data Index: 131229 (C4 (Web Text))

Max Activating Token Index: 835

Text #13

Max Range: 4.7737. Min Range: -4.7737

Max Act: 2.5265. Min Act: -0.0000

Data Index: 939675 (C4 (Web Text))

Max Activating Token Index: 645

Text #14

Max Range: 4.7737. Min Range: -4.7737

Max Act: 2.6282. Min Act: -0.0000

Data Index: 1172399 (C4 (Web Text))

Max Activating Token Index: 909

Text #15

Max Range: 4.7737. Min Range: -4.7737

Max Act: 1.9509. Min Act: -0.0000

Data Index: 683738 (C4 (Web Text))

Max Activating Token Index: 214

Text #16

Max Range: 4.7737. Min Range: -4.7737

Max Act: 1.8223. Min Act: -0.0000

Data Index: 713480 (C4 (Web Text))

Max Activating Token Index: 670

Text #17

Max Range: 4.7737. Min Range: -4.7737

Max Act: 1.8167. Min Act: -0.0000

Data Index: 807186 (C4 (Web Text))

Max Activating Token Index: 466

Text #18

Max Range: 4.7737. Min Range: -4.7737

Max Act: 1.8271. Min Act: -0.0000

Data Index: 991665 (C4 (Web Text))

Max Activating Token Index: 95

Text #19

Max Range: 4.7737. Min Range: -4.7737

Max Act: 1.6473. Min Act: -0.0000

Data Index: 784193 (C4 (Web Text))

Max Activating Token Index: 375