Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 476 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.8303. Min Range: -0.8303

Max Act: 0.8303. Min Act: -0.0001

Data Index: 652967 (C4 (Web Text))

Max Activating Token Index: 82

Text #1

Max Range: 0.8303. Min Range: -0.8303

Max Act: 0.6534. Min Act: -0.0000

Data Index: 1414736 (Python Code)

Max Activating Token Index: 596

Text #2

Max Range: 0.8303. Min Range: -0.8303

Max Act: 0.6131. Min Act: -0.0001

Data Index: 330859 (C4 (Web Text))

Max Activating Token Index: 219

Text #3

Max Range: 0.8303. Min Range: -0.8303

Max Act: 0.5873. Min Act: -0.0000

Data Index: 1544143 (Python Code)

Max Activating Token Index: 107

Text #4

Max Range: 0.8303. Min Range: -0.8303

Max Act: 0.5873. Min Act: -0.0000

Data Index: 1459637 (Python Code)

Max Activating Token Index: 423

Text #5

Max Range: 0.8303. Min Range: -0.8303

Max Act: 0.5387. Min Act: -0.0000

Data Index: 1068636 (C4 (Web Text))

Max Activating Token Index: 480

Text #6

Max Range: 0.8303. Min Range: -0.8303

Max Act: 0.5445. Min Act: -0.0001

Data Index: 572076 (C4 (Web Text))

Max Activating Token Index: 249

Text #7

Max Range: 0.8303. Min Range: -0.8303

Max Act: 0.5277. Min Act: -0.0000

Data Index: 1553034 (Python Code)

Max Activating Token Index: 590

Text #8

Max Range: 0.8303. Min Range: -0.8303

Max Act: 0.5472. Min Act: -0.0000

Data Index: 1646441 (Python Code)

Max Activating Token Index: 955

Text #9

Max Range: 0.8303. Min Range: -0.8303

Max Act: 0.5408. Min Act: -0.0001

Data Index: 1481633 (Python Code)

Max Activating Token Index: 204

Text #10

Max Range: 0.8303. Min Range: -0.8303

Max Act: 0.5094. Min Act: -0.0001

Data Index: 1578674 (Python Code)

Max Activating Token Index: 35

Text #11

Max Range: 0.8303. Min Range: -0.8303

Max Act: 0.5393. Min Act: -0.0001

Data Index: 1546725 (Python Code)

Max Activating Token Index: 624

Text #12

Max Range: 0.8303. Min Range: -0.8303

Max Act: 0.4981. Min Act: -0.0001

Data Index: 1536228 (Python Code)

Max Activating Token Index: 840

Text #13

Max Range: 0.8303. Min Range: -0.8303

Max Act: 0.4852. Min Act: -0.0000

Data Index: 1424872 (Python Code)

Max Activating Token Index: 325

Text #14

Max Range: 0.8303. Min Range: -0.8303

Max Act: 0.4362. Min Act: -0.0001

Data Index: 757073 (C4 (Web Text))

Max Activating Token Index: 534

Text #15

Max Range: 0.8303. Min Range: -0.8303

Max Act: 0.5101. Min Act: -0.0001

Data Index: 1566580 (Python Code)

Max Activating Token Index: 628

Text #16

Max Range: 0.8303. Min Range: -0.8303

Max Act: 0.5230. Min Act: -0.0000

Data Index: 1629633 (Python Code)

Max Activating Token Index: 43

Text #17

Max Range: 0.8303. Min Range: -0.8303

Max Act: 0.5063. Min Act: -0.0001

Data Index: 1397652 (Python Code)

Max Activating Token Index: 30

Text #18

Max Range: 0.8303. Min Range: -0.8303

Max Act: 0.5228. Min Act: -0.0001

Data Index: 1378239 (Python Code)

Max Activating Token Index: 132

Text #19

Max Range: 0.8303. Min Range: -0.8303

Max Act: 0.4700. Min Act: -0.0000

Data Index: 1392558 (Python Code)

Max Activating Token Index: 627