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

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

Neuron 1146 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: 1.6440. Min Range: -1.6440

Max Act: 1.6440. Min Act: -0.0000

Data Index: 452088 (C4 (Web Text))

Max Activating Token Index: 646

Text #1

Max Range: 1.6440. Min Range: -1.6440

Max Act: 1.5802. Min Act: -0.0000

Data Index: 1587502 (Python Code)

Max Activating Token Index: 796

Text #2

Max Range: 1.6440. Min Range: -1.6440

Max Act: 1.5832. Min Act: -0.0000

Data Index: 1161033 (C4 (Web Text))

Max Activating Token Index: 167

Text #3

Max Range: 1.6440. Min Range: -1.6440

Max Act: 1.4779. Min Act: -0.0000

Data Index: 1491050 (Python Code)

Max Activating Token Index: 16

Text #4

Max Range: 1.6440. Min Range: -1.6440

Max Act: 1.5504. Min Act: -0.0000

Data Index: 860175 (C4 (Web Text))

Max Activating Token Index: 335

Text #5

Max Range: 1.6440. Min Range: -1.6440

Max Act: 1.4625. Min Act: -0.0000

Data Index: 362717 (C4 (Web Text))

Max Activating Token Index: 371

Text #6

Max Range: 1.6440. Min Range: -1.6440

Max Act: 1.4377. Min Act: -0.0000

Data Index: 1578996 (Python Code)

Max Activating Token Index: 479

Text #7

Max Range: 1.6440. Min Range: -1.6440

Max Act: 1.3524. Min Act: -0.0000

Data Index: 575355 (C4 (Web Text))

Max Activating Token Index: 216

Text #8

Max Range: 1.6440. Min Range: -1.6440

Max Act: 1.3427. Min Act: -0.0000

Data Index: 1591179 (Python Code)

Max Activating Token Index: 95

Text #9

Max Range: 1.6440. Min Range: -1.6440

Max Act: 1.4102. Min Act: -0.0000

Data Index: 1583415 (Python Code)

Max Activating Token Index: 258

Text #10

Max Range: 1.6440. Min Range: -1.6440

Max Act: 1.4063. Min Act: -0.0000

Data Index: 975206 (C4 (Web Text))

Max Activating Token Index: 368

Text #11

Max Range: 1.6440. Min Range: -1.6440

Max Act: 1.4337. Min Act: -0.0000

Data Index: 523566 (C4 (Web Text))

Max Activating Token Index: 187

Text #12

Max Range: 1.6440. Min Range: -1.6440

Max Act: 1.3684. Min Act: -0.0000

Data Index: 538943 (C4 (Web Text))

Max Activating Token Index: 843

Text #13

Max Range: 1.6440. Min Range: -1.6440

Max Act: 1.2747. Min Act: -0.0000

Data Index: 1495755 (Python Code)

Max Activating Token Index: 251

Text #14

Max Range: 1.6440. Min Range: -1.6440

Max Act: 1.2396. Min Act: -0.0000

Data Index: 1613298 (Python Code)

Max Activating Token Index: 835

Text #15

Max Range: 1.6440. Min Range: -1.6440

Max Act: 1.1983. Min Act: -0.0000

Data Index: 1596049 (Python Code)

Max Activating Token Index: 329

Text #16

Max Range: 1.6440. Min Range: -1.6440

Max Act: 1.2064. Min Act: -0.0000

Data Index: 1616118 (Python Code)

Max Activating Token Index: 396

Text #17

Max Range: 1.6440. Min Range: -1.6440

Max Act: 1.1589. Min Act: -0.0000

Data Index: 921426 (C4 (Web Text))

Max Activating Token Index: 213

Text #18

Max Range: 1.6440. Min Range: -1.6440

Max Act: 1.1750. Min Act: -0.0000

Data Index: 1494839 (Python Code)

Max Activating Token Index: 187

Text #19

Max Range: 1.6440. Min Range: -1.6440

Max Act: 1.2192. Min Act: -0.0000

Data Index: 1113174 (C4 (Web Text))

Max Activating Token Index: 100