Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 43 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0482. Min Range: -0.0482

Max Act: 0.0482. Min Act: -0.0005

Data Index: 1470467 (Python Code)

Max Activating Token Index: 5

Text #1

Max Range: 0.0482. Min Range: -0.0482

Max Act: 0.0463. Min Act: -0.0005

Data Index: 1632648 (Python Code)

Max Activating Token Index: 4

Text #2

Max Range: 0.0482. Min Range: -0.0482

Max Act: 0.0410. Min Act: -0.0005

Data Index: 1374528 (Python Code)

Max Activating Token Index: 9

Text #3

Max Range: 0.0482. Min Range: -0.0482

Max Act: 0.0357. Min Act: -0.0005

Data Index: 1521558 (Python Code)

Max Activating Token Index: 12

Text #4

Max Range: 0.0482. Min Range: -0.0482

Max Act: 0.0203. Min Act: -0.0005

Data Index: 1550491 (Python Code)

Max Activating Token Index: 5

Text #5

Max Range: 0.0482. Min Range: -0.0482

Max Act: 0.0177. Min Act: -0.0005

Data Index: 1157009 (C4 (Web Text))

Max Activating Token Index: 12

Text #6

Max Range: 0.0482. Min Range: -0.0482

Max Act: 0.0162. Min Act: -0.0005

Data Index: 1575636 (Python Code)

Max Activating Token Index: 3

Text #7

Max Range: 0.0482. Min Range: -0.0482

Max Act: 0.0154. Min Act: -0.0005

Data Index: 58903 (C4 (Web Text))

Max Activating Token Index: 9

Text #8

Max Range: 0.0482. Min Range: -0.0482

Max Act: 0.0146. Min Act: -0.0005

Data Index: 1409000 (Python Code)

Max Activating Token Index: 6

Text #9

Max Range: 0.0482. Min Range: -0.0482

Max Act: 0.0144. Min Act: -0.0005

Data Index: 1190954 (C4 (Web Text))

Max Activating Token Index: 13

Text #10

Max Range: 0.0482. Min Range: -0.0482

Max Act: 0.0140. Min Act: -0.0005

Data Index: 1522261 (Python Code)

Max Activating Token Index: 5

Text #11

Max Range: 0.0482. Min Range: -0.0482

Max Act: 0.0130. Min Act: -0.0005

Data Index: 1224478 (C4 (Web Text))

Max Activating Token Index: 2

Text #12

Max Range: 0.0482. Min Range: -0.0482

Max Act: 0.0120. Min Act: -0.0005

Data Index: 859642 (C4 (Web Text))

Max Activating Token Index: 13

Text #13

Max Range: 0.0482. Min Range: -0.0482

Max Act: 0.0117. Min Act: -0.0005

Data Index: 162835 (C4 (Web Text))

Max Activating Token Index: 10

Text #14

Max Range: 0.0482. Min Range: -0.0482

Max Act: 0.0114. Min Act: -0.0005

Data Index: 1641725 (Python Code)

Max Activating Token Index: 2

Text #15

Max Range: 0.0482. Min Range: -0.0482

Max Act: 0.0114. Min Act: -0.0005

Data Index: 1361118 (Python Code)

Max Activating Token Index: 4

Text #16

Max Range: 0.0482. Min Range: -0.0482

Max Act: 0.0107. Min Act: -0.0005

Data Index: 724494 (C4 (Web Text))

Max Activating Token Index: 10

Text #17

Max Range: 0.0482. Min Range: -0.0482

Max Act: 0.0107. Min Act: -0.0005

Data Index: 1642199 (Python Code)

Max Activating Token Index: 9

Text #18

Max Range: 0.0482. Min Range: -0.0482

Max Act: 0.0107. Min Act: -0.0005

Data Index: 449123 (C4 (Web Text))

Max Activating Token Index: 7

Text #19

Max Range: 0.0482. Min Range: -0.0482

Max Act: 0.0106. Min Act: -0.0005

Data Index: 1586659 (Python Code)

Max Activating Token Index: 34