Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3342 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.1686. Min Range: -1.1686

Max Act: 1.1686. Min Act: -0.0000

Data Index: 773482 (C4 (Web Text))

Max Activating Token Index: 453

Text #1

Max Range: 1.1686. Min Range: -1.1686

Max Act: 0.8344. Min Act: -0.0001

Data Index: 1056587 (C4 (Web Text))

Max Activating Token Index: 647

Text #2

Max Range: 1.1686. Min Range: -1.1686

Max Act: 0.9475. Min Act: -0.0001

Data Index: 623474 (C4 (Web Text))

Max Activating Token Index: 250

Text #3

Max Range: 1.1686. Min Range: -1.1686

Max Act: 0.7500. Min Act: -0.0001

Data Index: 683929 (C4 (Web Text))

Max Activating Token Index: 493

Text #4

Max Range: 1.1686. Min Range: -1.1686

Max Act: 0.8281. Min Act: -0.0000

Data Index: 480168 (C4 (Web Text))

Max Activating Token Index: 796

Text #5

Max Range: 1.1686. Min Range: -1.1686

Max Act: 0.7708. Min Act: -0.0001

Data Index: 853981 (C4 (Web Text))

Max Activating Token Index: 446

Text #6

Max Range: 1.1686. Min Range: -1.1686

Max Act: 0.7803. Min Act: -0.0001

Data Index: 1412117 (Python Code)

Max Activating Token Index: 964

Text #7

Max Range: 1.1686. Min Range: -1.1686

Max Act: 0.6052. Min Act: -0.0001

Data Index: 763562 (C4 (Web Text))

Max Activating Token Index: 603

Text #8

Max Range: 1.1686. Min Range: -1.1686

Max Act: 0.7540. Min Act: 0.0000

Data Index: 1173447 (C4 (Web Text))

Max Activating Token Index: 398

Text #9

Max Range: 1.1686. Min Range: -1.1686

Max Act: 0.7485. Min Act: -0.0000

Data Index: 1012654 (C4 (Web Text))

Max Activating Token Index: 906

Text #10

Max Range: 1.1686. Min Range: -1.1686

Max Act: 0.7273. Min Act: -0.0000

Data Index: 1645635 (Python Code)

Max Activating Token Index: 1003

Text #11

Max Range: 1.1686. Min Range: -1.1686

Max Act: 0.7318. Min Act: -0.0001

Data Index: 1232272 (C4 (Web Text))

Max Activating Token Index: 339

Text #12

Max Range: 1.1686. Min Range: -1.1686

Max Act: 0.7050. Min Act: -0.0001

Data Index: 856701 (C4 (Web Text))

Max Activating Token Index: 902

Text #13

Max Range: 1.1686. Min Range: -1.1686

Max Act: 0.6321. Min Act: -0.0001

Data Index: 795210 (C4 (Web Text))

Max Activating Token Index: 455

Text #14

Max Range: 1.1686. Min Range: -1.1686

Max Act: 0.6309. Min Act: -0.0000

Data Index: 677542 (C4 (Web Text))

Max Activating Token Index: 745

Text #15

Max Range: 1.1686. Min Range: -1.1686

Max Act: 0.6469. Min Act: -0.0000

Data Index: 1012194 (C4 (Web Text))

Max Activating Token Index: 432

Text #16

Max Range: 1.1686. Min Range: -1.1686

Max Act: 0.7444. Min Act: -0.0001

Data Index: 1110779 (C4 (Web Text))

Max Activating Token Index: 656

Text #17

Max Range: 1.1686. Min Range: -1.1686

Max Act: 0.7311. Min Act: -0.0001

Data Index: 1445480 (Python Code)

Max Activating Token Index: 384

Text #18

Max Range: 1.1686. Min Range: -1.1686

Max Act: 0.5554. Min Act: -0.0000

Data Index: 455802 (C4 (Web Text))

Max Activating Token Index: 907

Text #19

Max Range: 1.1686. Min Range: -1.1686

Max Act: 0.7060. Min Act: 0.0000

Data Index: 938019 (C4 (Web Text))

Max Activating Token Index: 365