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

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

Neuron 2706 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3503. Min Range: -1.3503

Max Act: 1.3503. Min Act: -0.0000

Data Index: 79527 (C4 (Web Text))

Max Activating Token Index: 858

Text #1

Max Range: 1.3503. Min Range: -1.3503

Max Act: 1.0117. Min Act: -0.0000

Data Index: 1367267 (Python Code)

Max Activating Token Index: 306

Text #2

Max Range: 1.3503. Min Range: -1.3503

Max Act: 1.0039. Min Act: -0.0000

Data Index: 1601952 (Python Code)

Max Activating Token Index: 9

Text #3

Max Range: 1.3503. Min Range: -1.3503

Max Act: 0.9418. Min Act: -0.0000

Data Index: 382821 (C4 (Web Text))

Max Activating Token Index: 382

Text #4

Max Range: 1.3503. Min Range: -1.3503

Max Act: 0.9272. Min Act: -0.0000

Data Index: 1373020 (Python Code)

Max Activating Token Index: 263

Text #5

Max Range: 1.3503. Min Range: -1.3503

Max Act: 0.8467. Min Act: -0.0000

Data Index: 22985 (C4 (Web Text))

Max Activating Token Index: 537

Text #6

Max Range: 1.3503. Min Range: -1.3503

Max Act: 0.8620. Min Act: -0.0000

Data Index: 1421745 (Python Code)

Max Activating Token Index: 585

Text #7

Max Range: 1.3503. Min Range: -1.3503

Max Act: 0.8068. Min Act: -0.0000

Data Index: 938165 (C4 (Web Text))

Max Activating Token Index: 64

Text #8

Max Range: 1.3503. Min Range: -1.3503

Max Act: 0.7407. Min Act: -0.0000

Data Index: 115222 (C4 (Web Text))

Max Activating Token Index: 995

Text #9

Max Range: 1.3503. Min Range: -1.3503

Max Act: 0.8279. Min Act: -0.0000

Data Index: 1599466 (Python Code)

Max Activating Token Index: 535

Text #10

Max Range: 1.3503. Min Range: -1.3503

Max Act: 0.7947. Min Act: -0.0000

Data Index: 292107 (C4 (Web Text))

Max Activating Token Index: 450

Text #11

Max Range: 1.3503. Min Range: -1.3503

Max Act: 0.8120. Min Act: -0.0000

Data Index: 1438608 (Python Code)

Max Activating Token Index: 894

Text #12

Max Range: 1.3503. Min Range: -1.3503

Max Act: 0.8946. Min Act: -0.0000

Data Index: 1621693 (Python Code)

Max Activating Token Index: 199

Text #13

Max Range: 1.3503. Min Range: -1.3503

Max Act: 0.8307. Min Act: -0.0000

Data Index: 1630583 (Python Code)

Max Activating Token Index: 737

Text #14

Max Range: 1.3503. Min Range: -1.3503

Max Act: 0.8587. Min Act: -0.0000

Data Index: 1521990 (Python Code)

Max Activating Token Index: 353

Text #15

Max Range: 1.3503. Min Range: -1.3503

Max Act: 0.7549. Min Act: -0.0000

Data Index: 475968 (C4 (Web Text))

Max Activating Token Index: 248

Text #16

Max Range: 1.3503. Min Range: -1.3503

Max Act: 0.7894. Min Act: -0.0000

Data Index: 1572830 (Python Code)

Max Activating Token Index: 53

Text #17

Max Range: 1.3503. Min Range: -1.3503

Max Act: 0.7334. Min Act: -0.0000

Data Index: 1327831 (C4 (Web Text))

Max Activating Token Index: 463

Text #18

Max Range: 1.3503. Min Range: -1.3503

Max Act: 0.7782. Min Act: -0.0000

Data Index: 1505407 (Python Code)

Max Activating Token Index: 967

Text #19

Max Range: 1.3503. Min Range: -1.3503

Max Act: 0.7872. Min Act: -0.0000

Data Index: 1615413 (Python Code)

Max Activating Token Index: 827