Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 595 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.5055. Min Range: -1.5055

Max Act: 1.4490. Min Act: -0.0001

Data Index: 1145249 (C4 (Web Text))

Max Activating Token Index: 116

Text #1

Max Range: 1.5055. Min Range: -1.5055

Max Act: 1.4351. Min Act: -0.0001

Data Index: 539593 (C4 (Web Text))

Max Activating Token Index: 878

Text #2

Max Range: 1.5055. Min Range: -1.5055

Max Act: 1.5055. Min Act: -0.0001

Data Index: 958783 (C4 (Web Text))

Max Activating Token Index: 275

Text #3

Max Range: 1.5055. Min Range: -1.5055

Max Act: 1.3973. Min Act: -0.0001

Data Index: 257908 (C4 (Web Text))

Max Activating Token Index: 620

Text #4

Max Range: 1.5055. Min Range: -1.5055

Max Act: 1.3373. Min Act: -0.0001

Data Index: 1232089 (C4 (Web Text))

Max Activating Token Index: 423

Text #5

Max Range: 1.5055. Min Range: -1.5055

Max Act: 1.4262. Min Act: -0.0001

Data Index: 227021 (C4 (Web Text))

Max Activating Token Index: 878

Text #6

Max Range: 1.5055. Min Range: -1.5055

Max Act: 1.2728. Min Act: -0.0001

Data Index: 578332 (C4 (Web Text))

Max Activating Token Index: 605

Text #7

Max Range: 1.5055. Min Range: -1.5055

Max Act: 1.3101. Min Act: -0.0001

Data Index: 1178653 (C4 (Web Text))

Max Activating Token Index: 437

Text #8

Max Range: 1.5055. Min Range: -1.5055

Max Act: 1.2551. Min Act: -0.0001

Data Index: 552093 (C4 (Web Text))

Max Activating Token Index: 319

Text #9

Max Range: 1.5055. Min Range: -1.5055

Max Act: 1.2885. Min Act: -0.0001

Data Index: 525066 (C4 (Web Text))

Max Activating Token Index: 480

Text #10

Max Range: 1.5055. Min Range: -1.5055

Max Act: 1.1745. Min Act: -0.0001

Data Index: 1146173 (C4 (Web Text))

Max Activating Token Index: 425

Text #11

Max Range: 1.5055. Min Range: -1.5055

Max Act: 1.1582. Min Act: -0.0001

Data Index: 125308 (C4 (Web Text))

Max Activating Token Index: 423

Text #12

Max Range: 1.5055. Min Range: -1.5055

Max Act: 1.0364. Min Act: -0.0001

Data Index: 879191 (C4 (Web Text))

Max Activating Token Index: 872

Text #13

Max Range: 1.5055. Min Range: -1.5055

Max Act: 1.0680. Min Act: -0.0001

Data Index: 1251835 (C4 (Web Text))

Max Activating Token Index: 781

Text #14

Max Range: 1.5055. Min Range: -1.5055

Max Act: 0.9458. Min Act: -0.0001

Data Index: 1173010 (C4 (Web Text))

Max Activating Token Index: 966

Text #15

Max Range: 1.5055. Min Range: -1.5055

Max Act: 0.9415. Min Act: -0.0001

Data Index: 890487 (C4 (Web Text))

Max Activating Token Index: 99

Text #16

Max Range: 1.5055. Min Range: -1.5055

Max Act: 0.9291. Min Act: -0.0001

Data Index: 585713 (C4 (Web Text))

Max Activating Token Index: 1010

Text #17

Max Range: 1.5055. Min Range: -1.5055

Max Act: 0.9380. Min Act: -0.0001

Data Index: 378938 (C4 (Web Text))

Max Activating Token Index: 332

Text #18

Max Range: 1.5055. Min Range: -1.5055

Max Act: 0.9097. Min Act: -0.0001

Data Index: 433785 (C4 (Web Text))

Max Activating Token Index: 822

Text #19

Max Range: 1.5055. Min Range: -1.5055

Max Act: 0.9408. Min Act: -0.0001

Data Index: 1102279 (C4 (Web Text))

Max Activating Token Index: 14