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

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

Neuron 910 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: 2.4408. Min Range: -2.4408

Max Act: 2.4408. Min Act: -0.0000

Data Index: 1107250 (C4 (Web Text))

Max Activating Token Index: 641

Text #1

Max Range: 2.4408. Min Range: -2.4408

Max Act: 2.2867. Min Act: -0.0000

Data Index: 973124 (C4 (Web Text))

Max Activating Token Index: 847

Text #2

Max Range: 2.4408. Min Range: -2.4408

Max Act: 2.2564. Min Act: -0.0000

Data Index: 476320 (C4 (Web Text))

Max Activating Token Index: 262

Text #3

Max Range: 2.4408. Min Range: -2.4408

Max Act: 2.1134. Min Act: -0.0000

Data Index: 1189525 (C4 (Web Text))

Max Activating Token Index: 480

Text #4

Max Range: 2.4408. Min Range: -2.4408

Max Act: 2.0971. Min Act: -0.0000

Data Index: 1130567 (C4 (Web Text))

Max Activating Token Index: 234

Text #5

Max Range: 2.4408. Min Range: -2.4408

Max Act: 1.9008. Min Act: -0.0000

Data Index: 256666 (C4 (Web Text))

Max Activating Token Index: 829

Text #6

Max Range: 2.4408. Min Range: -2.4408

Max Act: 1.9758. Min Act: -0.0000

Data Index: 932102 (C4 (Web Text))

Max Activating Token Index: 777

Text #7

Max Range: 2.4408. Min Range: -2.4408

Max Act: 1.9516. Min Act: -0.0000

Data Index: 663458 (C4 (Web Text))

Max Activating Token Index: 454

Text #8

Max Range: 2.4408. Min Range: -2.4408

Max Act: 1.8317. Min Act: -0.0000

Data Index: 813129 (C4 (Web Text))

Max Activating Token Index: 556

Text #9

Max Range: 2.4408. Min Range: -2.4408

Max Act: 2.0188. Min Act: -0.0000

Data Index: 1286566 (C4 (Web Text))

Max Activating Token Index: 622

Text #10

Max Range: 2.4408. Min Range: -2.4408

Max Act: 1.7821. Min Act: -0.0000

Data Index: 1315519 (C4 (Web Text))

Max Activating Token Index: 308

Text #11

Max Range: 2.4408. Min Range: -2.4408

Max Act: 1.8760. Min Act: -0.0000

Data Index: 1071472 (C4 (Web Text))

Max Activating Token Index: 272

Text #12

Max Range: 2.4408. Min Range: -2.4408

Max Act: 1.8917. Min Act: -0.0000

Data Index: 815017 (C4 (Web Text))

Max Activating Token Index: 562

Text #13

Max Range: 2.4408. Min Range: -2.4408

Max Act: 1.9014. Min Act: -0.0000

Data Index: 459939 (C4 (Web Text))

Max Activating Token Index: 471

Text #14

Max Range: 2.4408. Min Range: -2.4408

Max Act: 1.6913. Min Act: -0.0000

Data Index: 252398 (C4 (Web Text))

Max Activating Token Index: 358

Text #15

Max Range: 2.4408. Min Range: -2.4408

Max Act: 1.7694. Min Act: -0.0000

Data Index: 732661 (C4 (Web Text))

Max Activating Token Index: 736

Text #16

Max Range: 2.4408. Min Range: -2.4408

Max Act: 1.9621. Min Act: -0.0000

Data Index: 288026 (C4 (Web Text))

Max Activating Token Index: 24

Text #17

Max Range: 2.4408. Min Range: -2.4408

Max Act: 1.7437. Min Act: -0.0000

Data Index: 207038 (C4 (Web Text))

Max Activating Token Index: 661

Text #18

Max Range: 2.4408. Min Range: -2.4408

Max Act: 1.6312. Min Act: -0.0000

Data Index: 71920 (C4 (Web Text))

Max Activating Token Index: 524

Text #19

Max Range: 2.4408. Min Range: -2.4408

Max Act: 1.6316. Min Act: -0.0000

Data Index: 599243 (C4 (Web Text))

Max Activating Token Index: 9