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

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

Neuron 536 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7016. Min Range: -0.7016

Max Act: 0.6388. Min Act: -0.0001

Data Index: 1643110 (Python Code)

Max Activating Token Index: 11

Text #1

Max Range: 0.7016. Min Range: -0.7016

Max Act: 0.6350. Min Act: -0.0001

Data Index: 1610848 (Python Code)

Max Activating Token Index: 400

Text #2

Max Range: 0.7016. Min Range: -0.7016

Max Act: 0.7016. Min Act: -0.0001

Data Index: 1362642 (Python Code)

Max Activating Token Index: 754

Text #3

Max Range: 0.7016. Min Range: -0.7016

Max Act: 0.6125. Min Act: -0.0001

Data Index: 1597682 (Python Code)

Max Activating Token Index: 84

Text #4

Max Range: 0.7016. Min Range: -0.7016

Max Act: 0.6774. Min Act: -0.0001

Data Index: 1516168 (Python Code)

Max Activating Token Index: 949

Text #5

Max Range: 0.7016. Min Range: -0.7016

Max Act: 0.6174. Min Act: -0.0001

Data Index: 1447193 (Python Code)

Max Activating Token Index: 890

Text #6

Max Range: 0.7016. Min Range: -0.7016

Max Act: 0.5999. Min Act: -0.0001

Data Index: 1498422 (Python Code)

Max Activating Token Index: 853

Text #7

Max Range: 0.7016. Min Range: -0.7016

Max Act: 0.5821. Min Act: -0.0001

Data Index: 1605963 (Python Code)

Max Activating Token Index: 198

Text #8

Max Range: 0.7016. Min Range: -0.7016

Max Act: 0.5298. Min Act: -0.0001

Data Index: 1474307 (Python Code)

Max Activating Token Index: 131

Text #9

Max Range: 0.7016. Min Range: -0.7016

Max Act: 0.5090. Min Act: -0.0001

Data Index: 1460687 (Python Code)

Max Activating Token Index: 148

Text #10

Max Range: 0.7016. Min Range: -0.7016

Max Act: 0.4951. Min Act: -0.0001

Data Index: 1517663 (Python Code)

Max Activating Token Index: 117

Text #11

Max Range: 0.7016. Min Range: -0.7016

Max Act: 0.5094. Min Act: -0.0001

Data Index: 1430517 (Python Code)

Max Activating Token Index: 4

Text #12

Max Range: 0.7016. Min Range: -0.7016

Max Act: 0.4780. Min Act: -0.0001

Data Index: 1522806 (Python Code)

Max Activating Token Index: 109

Text #13

Max Range: 0.7016. Min Range: -0.7016

Max Act: 0.5044. Min Act: -0.0001

Data Index: 1559592 (Python Code)

Max Activating Token Index: 90

Text #14

Max Range: 0.7016. Min Range: -0.7016

Max Act: 0.5356. Min Act: -0.0001

Data Index: 1511060 (Python Code)

Max Activating Token Index: 654

Text #15

Max Range: 0.7016. Min Range: -0.7016

Max Act: 0.4656. Min Act: -0.0001

Data Index: 1390997 (Python Code)

Max Activating Token Index: 176

Text #16

Max Range: 0.7016. Min Range: -0.7016

Max Act: 0.4740. Min Act: -0.0001

Data Index: 1549827 (Python Code)

Max Activating Token Index: 105

Text #17

Max Range: 0.7016. Min Range: -0.7016

Max Act: 0.4837. Min Act: -0.0001

Data Index: 1534050 (Python Code)

Max Activating Token Index: 571

Text #18

Max Range: 0.7016. Min Range: -0.7016

Max Act: 0.4658. Min Act: -0.0001

Data Index: 1407998 (Python Code)

Max Activating Token Index: 24

Text #19

Max Range: 0.7016. Min Range: -0.7016

Max Act: 0.4642. Min Act: -0.0001

Data Index: 1373903 (Python Code)

Max Activating Token Index: 957