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

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

Neuron 1385 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3386. Min Range: -1.3386

Max Act: 1.2043. Min Act: -0.0000

Data Index: 1192466 (C4 (Web Text))

Max Activating Token Index: 787

Text #1

Max Range: 1.3386. Min Range: -1.3386

Max Act: 1.2810. Min Act: -0.0000

Data Index: 1192946 (C4 (Web Text))

Max Activating Token Index: 544

Text #2

Max Range: 1.3386. Min Range: -1.3386

Max Act: 1.3386. Min Act: -0.0000

Data Index: 398300 (C4 (Web Text))

Max Activating Token Index: 839

Text #3

Max Range: 1.3386. Min Range: -1.3386

Max Act: 1.3371. Min Act: -0.0000

Data Index: 787057 (C4 (Web Text))

Max Activating Token Index: 458

Text #4

Max Range: 1.3386. Min Range: -1.3386

Max Act: 1.1663. Min Act: -0.0000

Data Index: 563797 (C4 (Web Text))

Max Activating Token Index: 332

Text #5

Max Range: 1.3386. Min Range: -1.3386

Max Act: 1.1785. Min Act: -0.0000

Data Index: 877603 (C4 (Web Text))

Max Activating Token Index: 105

Text #6

Max Range: 1.3386. Min Range: -1.3386

Max Act: 1.2110. Min Act: -0.0000

Data Index: 991063 (C4 (Web Text))

Max Activating Token Index: 293

Text #7

Max Range: 1.3386. Min Range: -1.3386

Max Act: 1.1393. Min Act: -0.0000

Data Index: 127542 (C4 (Web Text))

Max Activating Token Index: 97

Text #8

Max Range: 1.3386. Min Range: -1.3386

Max Act: 1.1476. Min Act: -0.0000

Data Index: 906475 (C4 (Web Text))

Max Activating Token Index: 564

Text #9

Max Range: 1.3386. Min Range: -1.3386

Max Act: 1.1410. Min Act: -0.0000

Data Index: 478591 (C4 (Web Text))

Max Activating Token Index: 126

Text #10

Max Range: 1.3386. Min Range: -1.3386

Max Act: 1.0842. Min Act: -0.0000

Data Index: 900671 (C4 (Web Text))

Max Activating Token Index: 317

Text #11

Max Range: 1.3386. Min Range: -1.3386

Max Act: 1.0825. Min Act: -0.0000

Data Index: 1620896 (Python Code)

Max Activating Token Index: 370

Text #12

Max Range: 1.3386. Min Range: -1.3386

Max Act: 1.0943. Min Act: -0.0000

Data Index: 284206 (C4 (Web Text))

Max Activating Token Index: 31

Text #13

Max Range: 1.3386. Min Range: -1.3386

Max Act: 1.0820. Min Act: -0.0000

Data Index: 93644 (C4 (Web Text))

Max Activating Token Index: 50

Text #14

Max Range: 1.3386. Min Range: -1.3386

Max Act: 1.1374. Min Act: -0.0000

Data Index: 965231 (C4 (Web Text))

Max Activating Token Index: 471

Text #15

Max Range: 1.3386. Min Range: -1.3386

Max Act: 1.1302. Min Act: -0.0000

Data Index: 484454 (C4 (Web Text))

Max Activating Token Index: 536

Text #16

Max Range: 1.3386. Min Range: -1.3386

Max Act: 0.9976. Min Act: -0.0000

Data Index: 1223467 (C4 (Web Text))

Max Activating Token Index: 178

Text #17

Max Range: 1.3386. Min Range: -1.3386

Max Act: 1.0612. Min Act: -0.0000

Data Index: 1036341 (C4 (Web Text))

Max Activating Token Index: 156

Text #18

Max Range: 1.3386. Min Range: -1.3386

Max Act: 1.0250. Min Act: -0.0000

Data Index: 1188760 (C4 (Web Text))

Max Activating Token Index: 395

Text #19

Max Range: 1.3386. Min Range: -1.3386

Max Act: 1.1018. Min Act: -0.0000

Data Index: 802375 (C4 (Web Text))

Max Activating Token Index: 73