Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3121 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.6943. Min Range: -1.6943

Max Act: 1.6392. Min Act: -0.0001

Data Index: 1416182 (Python Code)

Max Activating Token Index: 35

Text #1

Max Range: 1.6943. Min Range: -1.6943

Max Act: 1.6943. Min Act: -0.0001

Data Index: 1545470 (Python Code)

Max Activating Token Index: 921

Text #2

Max Range: 1.6943. Min Range: -1.6943

Max Act: 1.5427. Min Act: -0.0001

Data Index: 1534015 (Python Code)

Max Activating Token Index: 189

Text #3

Max Range: 1.6943. Min Range: -1.6943

Max Act: 1.4327. Min Act: -0.0001

Data Index: 1611088 (Python Code)

Max Activating Token Index: 402

Text #4

Max Range: 1.6943. Min Range: -1.6943

Max Act: 1.4649. Min Act: -0.0001

Data Index: 1559668 (Python Code)

Max Activating Token Index: 45

Text #5

Max Range: 1.6943. Min Range: -1.6943

Max Act: 1.3179. Min Act: -0.0001

Data Index: 1499482 (Python Code)

Max Activating Token Index: 673

Text #6

Max Range: 1.6943. Min Range: -1.6943

Max Act: 1.3399. Min Act: -0.0001

Data Index: 1479094 (Python Code)

Max Activating Token Index: 443

Text #7

Max Range: 1.6943. Min Range: -1.6943

Max Act: 1.3294. Min Act: -0.0001

Data Index: 1516115 (Python Code)

Max Activating Token Index: 386

Text #8

Max Range: 1.6943. Min Range: -1.6943

Max Act: 1.2908. Min Act: -0.0001

Data Index: 1525322 (Python Code)

Max Activating Token Index: 422

Text #9

Max Range: 1.6943. Min Range: -1.6943

Max Act: 1.3543. Min Act: -0.0001

Data Index: 1384181 (Python Code)

Max Activating Token Index: 391

Text #10

Max Range: 1.6943. Min Range: -1.6943

Max Act: 1.1555. Min Act: -0.0001

Data Index: 1604687 (Python Code)

Max Activating Token Index: 630

Text #11

Max Range: 1.6943. Min Range: -1.6943

Max Act: 1.3219. Min Act: -0.0001

Data Index: 1564471 (Python Code)

Max Activating Token Index: 30

Text #12

Max Range: 1.6943. Min Range: -1.6943

Max Act: 1.2768. Min Act: -0.0001

Data Index: 1643462 (Python Code)

Max Activating Token Index: 403

Text #13

Max Range: 1.6943. Min Range: -1.6943

Max Act: 1.2183. Min Act: -0.0001

Data Index: 1585695 (Python Code)

Max Activating Token Index: 624

Text #14

Max Range: 1.6943. Min Range: -1.6943

Max Act: 1.1789. Min Act: -0.0001

Data Index: 1615732 (Python Code)

Max Activating Token Index: 743

Text #15

Max Range: 1.6943. Min Range: -1.6943

Max Act: 1.1729. Min Act: -0.0001

Data Index: 1458582 (Python Code)

Max Activating Token Index: 44

Text #16

Max Range: 1.6943. Min Range: -1.6943

Max Act: 1.2372. Min Act: -0.0001

Data Index: 1619075 (Python Code)

Max Activating Token Index: 723

Text #17

Max Range: 1.6943. Min Range: -1.6943

Max Act: 1.2357. Min Act: -0.0001

Data Index: 760969 (C4 (Web Text))

Max Activating Token Index: 29

Text #18

Max Range: 1.6943. Min Range: -1.6943

Max Act: 1.2290. Min Act: -0.0001

Data Index: 1491256 (Python Code)

Max Activating Token Index: 86

Text #19

Max Range: 1.6943. Min Range: -1.6943

Max Act: 1.0434. Min Act: -0.0001

Data Index: 1635803 (Python Code)

Max Activating Token Index: 594