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

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

Neuron 355 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2131. Min Range: -2.2131

Max Act: 2.2131. Min Act: -0.0000

Data Index: 1544930 (Python Code)

Max Activating Token Index: 163

Text #1

Max Range: 2.2131. Min Range: -2.2131

Max Act: 1.9709. Min Act: -0.0000

Data Index: 1606564 (Python Code)

Max Activating Token Index: 1017

Text #2

Max Range: 2.2131. Min Range: -2.2131

Max Act: 1.9718. Min Act: -0.0000

Data Index: 1492522 (Python Code)

Max Activating Token Index: 943

Text #3

Max Range: 2.2131. Min Range: -2.2131

Max Act: 1.8511. Min Act: -0.0000

Data Index: 1656473 (Python Code)

Max Activating Token Index: 381

Text #4

Max Range: 2.2131. Min Range: -2.2131

Max Act: 2.0057. Min Act: -0.0000

Data Index: 1554309 (Python Code)

Max Activating Token Index: 850

Text #5

Max Range: 2.2131. Min Range: -2.2131

Max Act: 1.6869. Min Act: -0.0000

Data Index: 1650316 (Python Code)

Max Activating Token Index: 695

Text #6

Max Range: 2.2131. Min Range: -2.2131

Max Act: 1.6858. Min Act: -0.0000

Data Index: 1494998 (Python Code)

Max Activating Token Index: 106

Text #7

Max Range: 2.2131. Min Range: -2.2131

Max Act: 1.6377. Min Act: -0.0000

Data Index: 1521899 (Python Code)

Max Activating Token Index: 938

Text #8

Max Range: 2.2131. Min Range: -2.2131

Max Act: 1.6289. Min Act: -0.0000

Data Index: 1520332 (Python Code)

Max Activating Token Index: 95

Text #9

Max Range: 2.2131. Min Range: -2.2131

Max Act: 1.5430. Min Act: -0.0000

Data Index: 1573119 (Python Code)

Max Activating Token Index: 850

Text #10

Max Range: 2.2131. Min Range: -2.2131

Max Act: 1.4170. Min Act: -0.0000

Data Index: 1494598 (Python Code)

Max Activating Token Index: 821

Text #11

Max Range: 2.2131. Min Range: -2.2131

Max Act: 1.5957. Min Act: -0.0000

Data Index: 1373695 (Python Code)

Max Activating Token Index: 371

Text #12

Max Range: 2.2131. Min Range: -2.2131

Max Act: 1.6809. Min Act: -0.0000

Data Index: 1561364 (Python Code)

Max Activating Token Index: 46

Text #13

Max Range: 2.2131. Min Range: -2.2131

Max Act: 1.6817. Min Act: -0.0000

Data Index: 1541351 (Python Code)

Max Activating Token Index: 830

Text #14

Max Range: 2.2131. Min Range: -2.2131

Max Act: 1.6730. Min Act: -0.0000

Data Index: 1505899 (Python Code)

Max Activating Token Index: 210

Text #15

Max Range: 2.2131. Min Range: -2.2131

Max Act: 1.5500. Min Act: -0.0000

Data Index: 1620564 (Python Code)

Max Activating Token Index: 470

Text #16

Max Range: 2.2131. Min Range: -2.2131

Max Act: 1.4639. Min Act: -0.0000

Data Index: 1443993 (Python Code)

Max Activating Token Index: 320

Text #17

Max Range: 2.2131. Min Range: -2.2131

Max Act: 1.5275. Min Act: -0.0000

Data Index: 1398620 (Python Code)

Max Activating Token Index: 755

Text #18

Max Range: 2.2131. Min Range: -2.2131

Max Act: 1.4451. Min Act: -0.0000

Data Index: 1469064 (Python Code)

Max Activating Token Index: 574

Text #19

Max Range: 2.2131. Min Range: -2.2131

Max Act: 1.3552. Min Act: -0.0000

Data Index: 1577169 (Python Code)

Max Activating Token Index: 805