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

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

Neuron 5057 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8458. Min Range: -0.8458

Max Act: 0.8411. Min Act: -0.0000

Data Index: 1105686 (C4 (Web Text))

Max Activating Token Index: 580

Text #1

Max Range: 0.8458. Min Range: -0.8458

Max Act: 0.8458. Min Act: -0.0000

Data Index: 711495 (C4 (Web Text))

Max Activating Token Index: 720

Text #2

Max Range: 0.8458. Min Range: -0.8458

Max Act: 0.8205. Min Act: -0.0000

Data Index: 156497 (C4 (Web Text))

Max Activating Token Index: 312

Text #3

Max Range: 0.8458. Min Range: -0.8458

Max Act: 0.8004. Min Act: -0.0000

Data Index: 467593 (C4 (Web Text))

Max Activating Token Index: 273

Text #4

Max Range: 0.8458. Min Range: -0.8458

Max Act: 0.7583. Min Act: -0.0000

Data Index: 1446308 (Python Code)

Max Activating Token Index: 54

Text #5

Max Range: 0.8458. Min Range: -0.8458

Max Act: 0.7107. Min Act: -0.0000

Data Index: 533430 (C4 (Web Text))

Max Activating Token Index: 309

Text #6

Max Range: 0.8458. Min Range: -0.8458

Max Act: 0.6912. Min Act: -0.0000

Data Index: 1603865 (Python Code)

Max Activating Token Index: 98

Text #7

Max Range: 0.8458. Min Range: -0.8458

Max Act: 0.6627. Min Act: -0.0000

Data Index: 1534668 (Python Code)

Max Activating Token Index: 993

Text #8

Max Range: 0.8458. Min Range: -0.8458

Max Act: 0.5931. Min Act: -0.0000

Data Index: 1604830 (Python Code)

Max Activating Token Index: 632

Text #9

Max Range: 0.8458. Min Range: -0.8458

Max Act: 0.5378. Min Act: -0.0000

Data Index: 1585786 (Python Code)

Max Activating Token Index: 107

Text #10

Max Range: 0.8458. Min Range: -0.8458

Max Act: 0.6026. Min Act: -0.0000

Data Index: 1536249 (Python Code)

Max Activating Token Index: 425

Text #11

Max Range: 0.8458. Min Range: -0.8458

Max Act: 0.6784. Min Act: -0.0000

Data Index: 1656527 (Python Code)

Max Activating Token Index: 1016

Text #12

Max Range: 0.8458. Min Range: -0.8458

Max Act: 0.6236. Min Act: -0.0000

Data Index: 1170981 (C4 (Web Text))

Max Activating Token Index: 342

Text #13

Max Range: 0.8458. Min Range: -0.8458

Max Act: 0.6013. Min Act: -0.0000

Data Index: 1360866 (Python Code)

Max Activating Token Index: 283

Text #14

Max Range: 0.8458. Min Range: -0.8458

Max Act: 0.6677. Min Act: -0.0000

Data Index: 883524 (C4 (Web Text))

Max Activating Token Index: 105

Text #15

Max Range: 0.8458. Min Range: -0.8458

Max Act: 0.6097. Min Act: -0.0000

Data Index: 1004150 (C4 (Web Text))

Max Activating Token Index: 87

Text #16

Max Range: 0.8458. Min Range: -0.8458

Max Act: 0.5769. Min Act: -0.0000

Data Index: 1433451 (Python Code)

Max Activating Token Index: 624

Text #17

Max Range: 0.8458. Min Range: -0.8458

Max Act: 0.5409. Min Act: -0.0000

Data Index: 1549331 (Python Code)

Max Activating Token Index: 80

Text #18

Max Range: 0.8458. Min Range: -0.8458

Max Act: 0.6094. Min Act: -0.0000

Data Index: 1627204 (Python Code)

Max Activating Token Index: 1009

Text #19

Max Range: 0.8458. Min Range: -0.8458

Max Act: 0.5572. Min Act: -0.0000

Data Index: 1606092 (Python Code)

Max Activating Token Index: 295