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

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

Neuron 4100 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6566. Min Range: -3.6566

Max Act: 3.6566. Min Act: -0.0000

Data Index: 244943 (C4 (Web Text))

Max Activating Token Index: 971

Text #1

Max Range: 3.6566. Min Range: -3.6566

Max Act: 3.3285. Min Act: -0.0000

Data Index: 1432550 (Python Code)

Max Activating Token Index: 543

Text #2

Max Range: 3.6566. Min Range: -3.6566

Max Act: 3.2460. Min Act: -0.0000

Data Index: 1544252 (Python Code)

Max Activating Token Index: 339

Text #3

Max Range: 3.6566. Min Range: -3.6566

Max Act: 3.4348. Min Act: -0.0000

Data Index: 1546803 (Python Code)

Max Activating Token Index: 985

Text #4

Max Range: 3.6566. Min Range: -3.6566

Max Act: 3.3384. Min Act: -0.0000

Data Index: 1497867 (Python Code)

Max Activating Token Index: 500

Text #5

Max Range: 3.6566. Min Range: -3.6566

Max Act: 3.0053. Min Act: -0.0000

Data Index: 1048760 (C4 (Web Text))

Max Activating Token Index: 288

Text #6

Max Range: 3.6566. Min Range: -3.6566

Max Act: 3.2838. Min Act: -0.0000

Data Index: 633879 (C4 (Web Text))

Max Activating Token Index: 928

Text #7

Max Range: 3.6566. Min Range: -3.6566

Max Act: 3.1016. Min Act: -0.0000

Data Index: 1382356 (Python Code)

Max Activating Token Index: 699

Text #8

Max Range: 3.6566. Min Range: -3.6566

Max Act: 3.3276. Min Act: -0.0000

Data Index: 1300437 (C4 (Web Text))

Max Activating Token Index: 702

Text #9

Max Range: 3.6566. Min Range: -3.6566

Max Act: 3.0149. Min Act: -0.0000

Data Index: 255338 (C4 (Web Text))

Max Activating Token Index: 246

Text #10

Max Range: 3.6566. Min Range: -3.6566

Max Act: 3.1535. Min Act: -0.0000

Data Index: 1428945 (Python Code)

Max Activating Token Index: 643

Text #11

Max Range: 3.6566. Min Range: -3.6566

Max Act: 3.1148. Min Act: -0.0000

Data Index: 378784 (C4 (Web Text))

Max Activating Token Index: 433

Text #12

Max Range: 3.6566. Min Range: -3.6566

Max Act: 3.1521. Min Act: -0.0000

Data Index: 492484 (C4 (Web Text))

Max Activating Token Index: 872

Text #13

Max Range: 3.6566. Min Range: -3.6566

Max Act: 3.1152. Min Act: -0.0000

Data Index: 243559 (C4 (Web Text))

Max Activating Token Index: 557

Text #14

Max Range: 3.6566. Min Range: -3.6566

Max Act: 3.0938. Min Act: -0.0000

Data Index: 624776 (C4 (Web Text))

Max Activating Token Index: 562

Text #15

Max Range: 3.6566. Min Range: -3.6566

Max Act: 3.2166. Min Act: -0.0000

Data Index: 138873 (C4 (Web Text))

Max Activating Token Index: 362

Text #16

Max Range: 3.6566. Min Range: -3.6566

Max Act: 3.2470. Min Act: -0.0000

Data Index: 1511819 (Python Code)

Max Activating Token Index: 379

Text #17

Max Range: 3.6566. Min Range: -3.6566

Max Act: 2.9614. Min Act: -0.0000

Data Index: 1521346 (Python Code)

Max Activating Token Index: 981

Text #18

Max Range: 3.6566. Min Range: -3.6566

Max Act: 3.3381. Min Act: -0.0000

Data Index: 187981 (C4 (Web Text))

Max Activating Token Index: 312

Text #19

Max Range: 3.6566. Min Range: -3.6566

Max Act: 2.6401. Min Act: -0.0000

Data Index: 1067987 (C4 (Web Text))

Max Activating Token Index: 856