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

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

Neuron 2226 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7008. Min Range: -0.7008

Max Act: 0.7008. Min Act: -0.0000

Data Index: 69048 (C4 (Web Text))

Max Activating Token Index: 987

Text #1

Max Range: 0.7008. Min Range: -0.7008

Max Act: 0.4957. Min Act: -0.0000

Data Index: 701436 (C4 (Web Text))

Max Activating Token Index: 379

Text #2

Max Range: 0.7008. Min Range: -0.7008

Max Act: 0.4557. Min Act: -0.0000

Data Index: 247213 (C4 (Web Text))

Max Activating Token Index: 973

Text #3

Max Range: 0.7008. Min Range: -0.7008

Max Act: 0.4207. Min Act: -0.0000

Data Index: 1265278 (C4 (Web Text))

Max Activating Token Index: 772

Text #4

Max Range: 0.7008. Min Range: -0.7008

Max Act: 0.4110. Min Act: -0.0000

Data Index: 1050006 (C4 (Web Text))

Max Activating Token Index: 637

Text #5

Max Range: 0.7008. Min Range: -0.7008

Max Act: 0.3592. Min Act: -0.0000

Data Index: 180833 (C4 (Web Text))

Max Activating Token Index: 302

Text #6

Max Range: 0.7008. Min Range: -0.7008

Max Act: 0.3458. Min Act: -0.0000

Data Index: 481444 (C4 (Web Text))

Max Activating Token Index: 220

Text #7

Max Range: 0.7008. Min Range: -0.7008

Max Act: 0.3532. Min Act: -0.0000

Data Index: 352722 (C4 (Web Text))

Max Activating Token Index: 714

Text #8

Max Range: 0.7008. Min Range: -0.7008

Max Act: 0.3573. Min Act: -0.0000

Data Index: 543149 (C4 (Web Text))

Max Activating Token Index: 630

Text #9

Max Range: 0.7008. Min Range: -0.7008

Max Act: 0.3587. Min Act: -0.0000

Data Index: 858705 (C4 (Web Text))

Max Activating Token Index: 601

Text #10

Max Range: 0.7008. Min Range: -0.7008

Max Act: 0.3668. Min Act: -0.0000

Data Index: 976228 (C4 (Web Text))

Max Activating Token Index: 386

Text #11

Max Range: 0.7008. Min Range: -0.7008

Max Act: 0.3662. Min Act: -0.0000

Data Index: 1339916 (C4 (Web Text))

Max Activating Token Index: 836

Text #12

Max Range: 0.7008. Min Range: -0.7008

Max Act: 0.3422. Min Act: -0.0000

Data Index: 543599 (C4 (Web Text))

Max Activating Token Index: 621

Text #13

Max Range: 0.7008. Min Range: -0.7008

Max Act: 0.3549. Min Act: -0.0000

Data Index: 1092297 (C4 (Web Text))

Max Activating Token Index: 355

Text #14

Max Range: 0.7008. Min Range: -0.7008

Max Act: 0.3487. Min Act: -0.0000

Data Index: 940707 (C4 (Web Text))

Max Activating Token Index: 63

Text #15

Max Range: 0.7008. Min Range: -0.7008

Max Act: 0.3398. Min Act: -0.0000

Data Index: 1202243 (C4 (Web Text))

Max Activating Token Index: 84

Text #16

Max Range: 0.7008. Min Range: -0.7008

Max Act: 0.3534. Min Act: -0.0000

Data Index: 745683 (C4 (Web Text))

Max Activating Token Index: 717

Text #17

Max Range: 0.7008. Min Range: -0.7008

Max Act: 0.3413. Min Act: -0.0000

Data Index: 360609 (C4 (Web Text))

Max Activating Token Index: 758

Text #18

Max Range: 0.7008. Min Range: -0.7008

Max Act: 0.3493. Min Act: -0.0000

Data Index: 272999 (C4 (Web Text))

Max Activating Token Index: 580

Text #19

Max Range: 0.7008. Min Range: -0.7008

Max Act: 0.3368. Min Act: -0.0000

Data Index: 388651 (C4 (Web Text))

Max Activating Token Index: 1014