Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1545 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 3.3516. Min Range: -3.3516

Max Act: 3.3516. Min Act: -0.0000

Data Index: 39112 (C4 (Web Text))

Max Activating Token Index: 541

Text #1

Max Range: 3.3516. Min Range: -3.3516

Max Act: 3.0279. Min Act: -0.0000

Data Index: 355987 (C4 (Web Text))

Max Activating Token Index: 100

Text #2

Max Range: 3.3516. Min Range: -3.3516

Max Act: 2.9429. Min Act: -0.0000

Data Index: 482711 (C4 (Web Text))

Max Activating Token Index: 9

Text #3

Max Range: 3.3516. Min Range: -3.3516

Max Act: 2.9514. Min Act: -0.0000

Data Index: 631318 (C4 (Web Text))

Max Activating Token Index: 937

Text #4

Max Range: 3.3516. Min Range: -3.3516

Max Act: 2.8557. Min Act: -0.0000

Data Index: 815250 (C4 (Web Text))

Max Activating Token Index: 570

Text #5

Max Range: 3.3516. Min Range: -3.3516

Max Act: 3.0563. Min Act: -0.0000

Data Index: 595583 (C4 (Web Text))

Max Activating Token Index: 663

Text #6

Max Range: 3.3516. Min Range: -3.3516

Max Act: 2.7470. Min Act: -0.0000

Data Index: 324738 (C4 (Web Text))

Max Activating Token Index: 355

Text #7

Max Range: 3.3516. Min Range: -3.3516

Max Act: 2.8200. Min Act: -0.0000

Data Index: 1045962 (C4 (Web Text))

Max Activating Token Index: 65

Text #8

Max Range: 3.3516. Min Range: -3.3516

Max Act: 2.5725. Min Act: -0.0000

Data Index: 1355189 (C4 (Web Text))

Max Activating Token Index: 555

Text #9

Max Range: 3.3516. Min Range: -3.3516

Max Act: 2.8204. Min Act: -0.0000

Data Index: 884438 (C4 (Web Text))

Max Activating Token Index: 16

Text #10

Max Range: 3.3516. Min Range: -3.3516

Max Act: 2.9415. Min Act: -0.0000

Data Index: 273737 (C4 (Web Text))

Max Activating Token Index: 941

Text #11

Max Range: 3.3516. Min Range: -3.3516

Max Act: 2.7573. Min Act: -0.0000

Data Index: 1149230 (C4 (Web Text))

Max Activating Token Index: 509

Text #12

Max Range: 3.3516. Min Range: -3.3516

Max Act: 2.7558. Min Act: -0.0000

Data Index: 539039 (C4 (Web Text))

Max Activating Token Index: 494

Text #13

Max Range: 3.3516. Min Range: -3.3516

Max Act: 2.6266. Min Act: -0.0000

Data Index: 237115 (C4 (Web Text))

Max Activating Token Index: 514

Text #14

Max Range: 3.3516. Min Range: -3.3516

Max Act: 3.0258. Min Act: -0.0000

Data Index: 838192 (C4 (Web Text))

Max Activating Token Index: 143

Text #15

Max Range: 3.3516. Min Range: -3.3516

Max Act: 2.6037. Min Act: -0.0000

Data Index: 887916 (C4 (Web Text))

Max Activating Token Index: 867

Text #16

Max Range: 3.3516. Min Range: -3.3516

Max Act: 2.7227. Min Act: -0.0000

Data Index: 806716 (C4 (Web Text))

Max Activating Token Index: 800

Text #17

Max Range: 3.3516. Min Range: -3.3516

Max Act: 2.6944. Min Act: -0.0000

Data Index: 266987 (C4 (Web Text))

Max Activating Token Index: 40

Text #18

Max Range: 3.3516. Min Range: -3.3516

Max Act: 2.5802. Min Act: -0.0000

Data Index: 1100732 (C4 (Web Text))

Max Activating Token Index: 791

Text #19

Max Range: 3.3516. Min Range: -3.3516

Max Act: 2.8066. Min Act: -0.0000

Data Index: 527097 (C4 (Web Text))

Max Activating Token Index: 514