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

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

Neuron 114 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6019. Min Range: -0.6019

Max Act: 0.6019. Min Act: -0.0000

Data Index: 1436722 (Python Code)

Max Activating Token Index: 270

Text #1

Max Range: 0.6019. Min Range: -0.6019

Max Act: 0.5446. Min Act: -0.0000

Data Index: 1583438 (Python Code)

Max Activating Token Index: 276

Text #2

Max Range: 0.6019. Min Range: -0.6019

Max Act: 0.5519. Min Act: -0.0000

Data Index: 1554175 (Python Code)

Max Activating Token Index: 442

Text #3

Max Range: 0.6019. Min Range: -0.6019

Max Act: 0.5207. Min Act: -0.0000

Data Index: 1397955 (Python Code)

Max Activating Token Index: 769

Text #4

Max Range: 0.6019. Min Range: -0.6019

Max Act: 0.5339. Min Act: -0.0000

Data Index: 1432723 (Python Code)

Max Activating Token Index: 495

Text #5

Max Range: 0.6019. Min Range: -0.6019

Max Act: 0.5121. Min Act: -0.0000

Data Index: 1394074 (Python Code)

Max Activating Token Index: 416

Text #6

Max Range: 0.6019. Min Range: -0.6019

Max Act: 0.5225. Min Act: -0.0000

Data Index: 1370689 (Python Code)

Max Activating Token Index: 214

Text #7

Max Range: 0.6019. Min Range: -0.6019

Max Act: 0.4988. Min Act: -0.0000

Data Index: 1645938 (Python Code)

Max Activating Token Index: 1013

Text #8

Max Range: 0.6019. Min Range: -0.6019

Max Act: 0.4958. Min Act: -0.0000

Data Index: 1461789 (Python Code)

Max Activating Token Index: 991

Text #9

Max Range: 0.6019. Min Range: -0.6019

Max Act: 0.4867. Min Act: -0.0001

Data Index: 1642335 (Python Code)

Max Activating Token Index: 406

Text #10

Max Range: 0.6019. Min Range: -0.6019

Max Act: 0.4981. Min Act: -0.0000

Data Index: 1385885 (Python Code)

Max Activating Token Index: 452

Text #11

Max Range: 0.6019. Min Range: -0.6019

Max Act: 0.4832. Min Act: -0.0000

Data Index: 1448727 (Python Code)

Max Activating Token Index: 613

Text #12

Max Range: 0.6019. Min Range: -0.6019

Max Act: 0.5167. Min Act: -0.0000

Data Index: 1631624 (Python Code)

Max Activating Token Index: 62

Text #13

Max Range: 0.6019. Min Range: -0.6019

Max Act: 0.4809. Min Act: -0.0000

Data Index: 1620081 (Python Code)

Max Activating Token Index: 301

Text #14

Max Range: 0.6019. Min Range: -0.6019

Max Act: 0.4772. Min Act: -0.0001

Data Index: 1586720 (Python Code)

Max Activating Token Index: 36

Text #15

Max Range: 0.6019. Min Range: -0.6019

Max Act: 0.4875. Min Act: -0.0001

Data Index: 1596591 (Python Code)

Max Activating Token Index: 879

Text #16

Max Range: 0.6019. Min Range: -0.6019

Max Act: 0.4878. Min Act: -0.0000

Data Index: 1472047 (Python Code)

Max Activating Token Index: 307

Text #17

Max Range: 0.6019. Min Range: -0.6019

Max Act: 0.4821. Min Act: -0.0001

Data Index: 1647073 (Python Code)

Max Activating Token Index: 187

Text #18

Max Range: 0.6019. Min Range: -0.6019

Max Act: 0.4805. Min Act: -0.0001

Data Index: 1556400 (Python Code)

Max Activating Token Index: 87

Text #19

Max Range: 0.6019. Min Range: -0.6019

Max Act: 0.4967. Min Act: -0.0000

Data Index: 1628113 (Python Code)

Max Activating Token Index: 309