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

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

Neuron 2605 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8292. Min Range: -2.8292

Max Act: 2.8292. Min Act: -0.0000

Data Index: 457081 (C4 (Web Text))

Max Activating Token Index: 492

Text #1

Max Range: 2.8292. Min Range: -2.8292

Max Act: 2.5537. Min Act: -0.0000

Data Index: 1152779 (C4 (Web Text))

Max Activating Token Index: 614

Text #2

Max Range: 2.8292. Min Range: -2.8292

Max Act: 2.1860. Min Act: -0.0000

Data Index: 676068 (C4 (Web Text))

Max Activating Token Index: 265

Text #3

Max Range: 2.8292. Min Range: -2.8292

Max Act: 1.7753. Min Act: -0.0000

Data Index: 794530 (C4 (Web Text))

Max Activating Token Index: 746

Text #4

Max Range: 2.8292. Min Range: -2.8292

Max Act: 2.0967. Min Act: -0.0000

Data Index: 563175 (C4 (Web Text))

Max Activating Token Index: 696

Text #5

Max Range: 2.8292. Min Range: -2.8292

Max Act: 1.8913. Min Act: -0.0000

Data Index: 724296 (C4 (Web Text))

Max Activating Token Index: 727

Text #6

Max Range: 2.8292. Min Range: -2.8292

Max Act: 1.8722. Min Act: -0.0000

Data Index: 526135 (C4 (Web Text))

Max Activating Token Index: 586

Text #7

Max Range: 2.8292. Min Range: -2.8292

Max Act: 1.8702. Min Act: -0.0000

Data Index: 661339 (C4 (Web Text))

Max Activating Token Index: 555

Text #8

Max Range: 2.8292. Min Range: -2.8292

Max Act: 1.7554. Min Act: -0.0000

Data Index: 515255 (C4 (Web Text))

Max Activating Token Index: 401

Text #9

Max Range: 2.8292. Min Range: -2.8292

Max Act: 1.9317. Min Act: -0.0000

Data Index: 233202 (C4 (Web Text))

Max Activating Token Index: 991

Text #10

Max Range: 2.8292. Min Range: -2.8292

Max Act: 1.8857. Min Act: -0.0000

Data Index: 1099177 (C4 (Web Text))

Max Activating Token Index: 705

Text #11

Max Range: 2.8292. Min Range: -2.8292

Max Act: 1.7787. Min Act: -0.0000

Data Index: 1269260 (C4 (Web Text))

Max Activating Token Index: 921

Text #12

Max Range: 2.8292. Min Range: -2.8292

Max Act: 1.7722. Min Act: -0.0000

Data Index: 251063 (C4 (Web Text))

Max Activating Token Index: 942

Text #13

Max Range: 2.8292. Min Range: -2.8292

Max Act: 1.7561. Min Act: -0.0000

Data Index: 445334 (C4 (Web Text))

Max Activating Token Index: 433

Text #14

Max Range: 2.8292. Min Range: -2.8292

Max Act: 1.6766. Min Act: -0.0000

Data Index: 110331 (C4 (Web Text))

Max Activating Token Index: 932

Text #15

Max Range: 2.8292. Min Range: -2.8292

Max Act: 1.7343. Min Act: -0.0000

Data Index: 335543 (C4 (Web Text))

Max Activating Token Index: 1004

Text #16

Max Range: 2.8292. Min Range: -2.8292

Max Act: 1.7138. Min Act: -0.0000

Data Index: 1219928 (C4 (Web Text))

Max Activating Token Index: 418

Text #17

Max Range: 2.8292. Min Range: -2.8292

Max Act: 1.6897. Min Act: -0.0000

Data Index: 312336 (C4 (Web Text))

Max Activating Token Index: 774

Text #18

Max Range: 2.8292. Min Range: -2.8292

Max Act: 1.5937. Min Act: -0.0000

Data Index: 211821 (C4 (Web Text))

Max Activating Token Index: 312

Text #19

Max Range: 2.8292. Min Range: -2.8292

Max Act: 1.6860. Min Act: -0.0000

Data Index: 1206240 (C4 (Web Text))

Max Activating Token Index: 905