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

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

Neuron 624 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6876. Min Range: -0.6876

Max Act: 0.6876. Min Act: -0.0001

Data Index: 94864 (C4 (Web Text))

Max Activating Token Index: 101

Text #1

Max Range: 0.6876. Min Range: -0.6876

Max Act: 0.6186. Min Act: -0.0001

Data Index: 928076 (C4 (Web Text))

Max Activating Token Index: 921

Text #2

Max Range: 0.6876. Min Range: -0.6876

Max Act: 0.5875. Min Act: -0.0001

Data Index: 43421 (C4 (Web Text))

Max Activating Token Index: 145

Text #3

Max Range: 0.6876. Min Range: -0.6876

Max Act: 0.5583. Min Act: -0.0001

Data Index: 430592 (C4 (Web Text))

Max Activating Token Index: 207

Text #4

Max Range: 0.6876. Min Range: -0.6876

Max Act: 0.5507. Min Act: -0.0001

Data Index: 325920 (C4 (Web Text))

Max Activating Token Index: 905

Text #5

Max Range: 0.6876. Min Range: -0.6876

Max Act: 0.4877. Min Act: -0.0001

Data Index: 62105 (C4 (Web Text))

Max Activating Token Index: 534

Text #6

Max Range: 0.6876. Min Range: -0.6876

Max Act: 0.5396. Min Act: -0.0001

Data Index: 1021795 (C4 (Web Text))

Max Activating Token Index: 910

Text #7

Max Range: 0.6876. Min Range: -0.6876

Max Act: 0.5219. Min Act: -0.0001

Data Index: 682061 (C4 (Web Text))

Max Activating Token Index: 935

Text #8

Max Range: 0.6876. Min Range: -0.6876

Max Act: 0.5075. Min Act: -0.0001

Data Index: 425815 (C4 (Web Text))

Max Activating Token Index: 755

Text #9

Max Range: 0.6876. Min Range: -0.6876

Max Act: 0.5586. Min Act: -0.0001

Data Index: 812737 (C4 (Web Text))

Max Activating Token Index: 933

Text #10

Max Range: 0.6876. Min Range: -0.6876

Max Act: 0.5290. Min Act: -0.0001

Data Index: 20045 (C4 (Web Text))

Max Activating Token Index: 310

Text #11

Max Range: 0.6876. Min Range: -0.6876

Max Act: 0.5579. Min Act: -0.0001

Data Index: 1164996 (C4 (Web Text))

Max Activating Token Index: 934

Text #12

Max Range: 0.6876. Min Range: -0.6876

Max Act: 0.5373. Min Act: -0.0001

Data Index: 624907 (C4 (Web Text))

Max Activating Token Index: 16

Text #13

Max Range: 0.6876. Min Range: -0.6876

Max Act: 0.5011. Min Act: -0.0001

Data Index: 273380 (C4 (Web Text))

Max Activating Token Index: 57

Text #14

Max Range: 0.6876. Min Range: -0.6876

Max Act: 0.5132. Min Act: -0.0001

Data Index: 1259318 (C4 (Web Text))

Max Activating Token Index: 924

Text #15

Max Range: 0.6876. Min Range: -0.6876

Max Act: 0.4593. Min Act: -0.0001

Data Index: 149286 (C4 (Web Text))

Max Activating Token Index: 297

Text #16

Max Range: 0.6876. Min Range: -0.6876

Max Act: 0.5198. Min Act: -0.0001

Data Index: 1204006 (C4 (Web Text))

Max Activating Token Index: 140

Text #17

Max Range: 0.6876. Min Range: -0.6876

Max Act: 0.5323. Min Act: -0.0001

Data Index: 1274337 (C4 (Web Text))

Max Activating Token Index: 783

Text #18

Max Range: 0.6876. Min Range: -0.6876

Max Act: 0.4998. Min Act: -0.0001

Data Index: 718279 (C4 (Web Text))

Max Activating Token Index: 7

Text #19

Max Range: 0.6876. Min Range: -0.6876

Max Act: 0.5144. Min Act: -0.0001

Data Index: 611187 (C4 (Web Text))

Max Activating Token Index: 140