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

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

Neuron 4867 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: 3.7595. Min Range: -3.7595

Max Act: 3.7595. Min Act: -0.0000

Data Index: 1516718 (Python Code)

Max Activating Token Index: 806

Text #1

Max Range: 3.7595. Min Range: -3.7595

Max Act: 3.3768. Min Act: -0.0000

Data Index: 1415462 (Python Code)

Max Activating Token Index: 761

Text #2

Max Range: 3.7595. Min Range: -3.7595

Max Act: 3.2994. Min Act: -0.0000

Data Index: 571962 (C4 (Web Text))

Max Activating Token Index: 987

Text #3

Max Range: 3.7595. Min Range: -3.7595

Max Act: 3.1634. Min Act: -0.0000

Data Index: 910386 (C4 (Web Text))

Max Activating Token Index: 967

Text #4

Max Range: 3.7595. Min Range: -3.7595

Max Act: 3.2805. Min Act: -0.0000

Data Index: 1579760 (Python Code)

Max Activating Token Index: 758

Text #5

Max Range: 3.7595. Min Range: -3.7595

Max Act: 2.7831. Min Act: -0.0000

Data Index: 1173349 (C4 (Web Text))

Max Activating Token Index: 609

Text #6

Max Range: 3.7595. Min Range: -3.7595

Max Act: 3.1836. Min Act: -0.0000

Data Index: 1374353 (Python Code)

Max Activating Token Index: 975

Text #7

Max Range: 3.7595. Min Range: -3.7595

Max Act: 3.1593. Min Act: -0.0000

Data Index: 1522474 (Python Code)

Max Activating Token Index: 225

Text #8

Max Range: 3.7595. Min Range: -3.7595

Max Act: 2.9132. Min Act: -0.0000

Data Index: 1495056 (Python Code)

Max Activating Token Index: 281

Text #9

Max Range: 3.7595. Min Range: -3.7595

Max Act: 3.0027. Min Act: -0.0000

Data Index: 123288 (C4 (Web Text))

Max Activating Token Index: 1013

Text #10

Max Range: 3.7595. Min Range: -3.7595

Max Act: 3.1461. Min Act: -0.0000

Data Index: 491349 (C4 (Web Text))

Max Activating Token Index: 892

Text #11

Max Range: 3.7595. Min Range: -3.7595

Max Act: 2.8125. Min Act: -0.0000

Data Index: 1580590 (Python Code)

Max Activating Token Index: 381

Text #12

Max Range: 3.7595. Min Range: -3.7595

Max Act: 2.7677. Min Act: -0.0000

Data Index: 1572326 (Python Code)

Max Activating Token Index: 860

Text #13

Max Range: 3.7595. Min Range: -3.7595

Max Act: 2.9291. Min Act: -0.0000

Data Index: 1577174 (Python Code)

Max Activating Token Index: 539

Text #14

Max Range: 3.7595. Min Range: -3.7595

Max Act: 2.9093. Min Act: -0.0000

Data Index: 986690 (C4 (Web Text))

Max Activating Token Index: 351

Text #15

Max Range: 3.7595. Min Range: -3.7595

Max Act: 2.8507. Min Act: -0.0000

Data Index: 450220 (C4 (Web Text))

Max Activating Token Index: 932

Text #16

Max Range: 3.7595. Min Range: -3.7595

Max Act: 2.7233. Min Act: -0.0000

Data Index: 1411316 (Python Code)

Max Activating Token Index: 608

Text #17

Max Range: 3.7595. Min Range: -3.7595

Max Act: 2.8374. Min Act: -0.0000

Data Index: 1579624 (Python Code)

Max Activating Token Index: 370

Text #18

Max Range: 3.7595. Min Range: -3.7595

Max Act: 2.9393. Min Act: -0.0000

Data Index: 1339109 (C4 (Web Text))

Max Activating Token Index: 616

Text #19

Max Range: 3.7595. Min Range: -3.7595

Max Act: 2.7993. Min Act: -0.0000

Data Index: 1583892 (Python Code)

Max Activating Token Index: 680