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

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

Neuron 4932 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2494. Min Range: -2.2494

Max Act: 2.2494. Min Act: -0.0000

Data Index: 827664 (C4 (Web Text))

Max Activating Token Index: 341

Text #1

Max Range: 2.2494. Min Range: -2.2494

Max Act: 2.0976. Min Act: 0.0000

Data Index: 164385 (C4 (Web Text))

Max Activating Token Index: 408

Text #2

Max Range: 2.2494. Min Range: -2.2494

Max Act: 2.1283. Min Act: 0.0001

Data Index: 699866 (C4 (Web Text))

Max Activating Token Index: 295

Text #3

Max Range: 2.2494. Min Range: -2.2494

Max Act: 1.9420. Min Act: 0.0000

Data Index: 1241650 (C4 (Web Text))

Max Activating Token Index: 535

Text #4

Max Range: 2.2494. Min Range: -2.2494

Max Act: 1.8442. Min Act: 0.0000

Data Index: 745773 (C4 (Web Text))

Max Activating Token Index: 839

Text #5

Max Range: 2.2494. Min Range: -2.2494

Max Act: 1.6801. Min Act: 0.0001

Data Index: 785309 (C4 (Web Text))

Max Activating Token Index: 890

Text #6

Max Range: 2.2494. Min Range: -2.2494

Max Act: 1.6475. Min Act: 0.0001

Data Index: 721696 (C4 (Web Text))

Max Activating Token Index: 300

Text #7

Max Range: 2.2494. Min Range: -2.2494

Max Act: 1.6521. Min Act: -0.0000

Data Index: 961390 (C4 (Web Text))

Max Activating Token Index: 553

Text #8

Max Range: 2.2494. Min Range: -2.2494

Max Act: 1.7207. Min Act: -0.0000

Data Index: 380596 (C4 (Web Text))

Max Activating Token Index: 370

Text #9

Max Range: 2.2494. Min Range: -2.2494

Max Act: 1.6970. Min Act: 0.0000

Data Index: 711425 (C4 (Web Text))

Max Activating Token Index: 654

Text #10

Max Range: 2.2494. Min Range: -2.2494

Max Act: 1.6448. Min Act: -0.0000

Data Index: 855565 (C4 (Web Text))

Max Activating Token Index: 229

Text #11

Max Range: 2.2494. Min Range: -2.2494

Max Act: 1.6300. Min Act: 0.0000

Data Index: 334384 (C4 (Web Text))

Max Activating Token Index: 478

Text #12

Max Range: 2.2494. Min Range: -2.2494

Max Act: 1.7053. Min Act: 0.0001

Data Index: 932017 (C4 (Web Text))

Max Activating Token Index: 1019

Text #13

Max Range: 2.2494. Min Range: -2.2494

Max Act: 1.5920. Min Act: -0.0000

Data Index: 666247 (C4 (Web Text))

Max Activating Token Index: 977

Text #14

Max Range: 2.2494. Min Range: -2.2494

Max Act: 1.5743. Min Act: 0.0001

Data Index: 521091 (C4 (Web Text))

Max Activating Token Index: 388

Text #15

Max Range: 2.2494. Min Range: -2.2494

Max Act: 1.6364. Min Act: -0.0000

Data Index: 488831 (C4 (Web Text))

Max Activating Token Index: 216

Text #16

Max Range: 2.2494. Min Range: -2.2494

Max Act: 1.5502. Min Act: -0.0000

Data Index: 516948 (C4 (Web Text))

Max Activating Token Index: 421

Text #17

Max Range: 2.2494. Min Range: -2.2494

Max Act: 1.5509. Min Act: -0.0000

Data Index: 1146172 (C4 (Web Text))

Max Activating Token Index: 440

Text #18

Max Range: 2.2494. Min Range: -2.2494

Max Act: 1.5378. Min Act: 0.0001

Data Index: 376412 (C4 (Web Text))

Max Activating Token Index: 96

Text #19

Max Range: 2.2494. Min Range: -2.2494

Max Act: 1.5358. Min Act: 0.0000

Data Index: 1210329 (C4 (Web Text))

Max Activating Token Index: 555