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

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

Neuron 1047 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: 0.7188. Min Range: -0.7188

Max Act: 0.7188. Min Act: -0.0001

Data Index: 236736 (C4 (Web Text))

Max Activating Token Index: 181

Text #1

Max Range: 0.7188. Min Range: -0.7188

Max Act: 0.7086. Min Act: -0.0001

Data Index: 333423 (C4 (Web Text))

Max Activating Token Index: 106

Text #2

Max Range: 0.7188. Min Range: -0.7188

Max Act: 0.6647. Min Act: -0.0001

Data Index: 720601 (C4 (Web Text))

Max Activating Token Index: 676

Text #3

Max Range: 0.7188. Min Range: -0.7188

Max Act: 0.6529. Min Act: -0.0000

Data Index: 1307453 (C4 (Web Text))

Max Activating Token Index: 693

Text #4

Max Range: 0.7188. Min Range: -0.7188

Max Act: 0.6350. Min Act: -0.0001

Data Index: 1166605 (C4 (Web Text))

Max Activating Token Index: 876

Text #5

Max Range: 0.7188. Min Range: -0.7188

Max Act: 0.6389. Min Act: -0.0000

Data Index: 165200 (C4 (Web Text))

Max Activating Token Index: 102

Text #6

Max Range: 0.7188. Min Range: -0.7188

Max Act: 0.6269. Min Act: -0.0001

Data Index: 642428 (C4 (Web Text))

Max Activating Token Index: 670

Text #7

Max Range: 0.7188. Min Range: -0.7188

Max Act: 0.6281. Min Act: -0.0000

Data Index: 841557 (C4 (Web Text))

Max Activating Token Index: 60

Text #8

Max Range: 0.7188. Min Range: -0.7188

Max Act: 0.6381. Min Act: -0.0001

Data Index: 263360 (C4 (Web Text))

Max Activating Token Index: 748

Text #9

Max Range: 0.7188. Min Range: -0.7188

Max Act: 0.6110. Min Act: -0.0001

Data Index: 1468076 (Python Code)

Max Activating Token Index: 536

Text #10

Max Range: 0.7188. Min Range: -0.7188

Max Act: 0.5827. Min Act: -0.0000

Data Index: 893496 (C4 (Web Text))

Max Activating Token Index: 684

Text #11

Max Range: 0.7188. Min Range: -0.7188

Max Act: 0.5788. Min Act: -0.0000

Data Index: 206719 (C4 (Web Text))

Max Activating Token Index: 759

Text #12

Max Range: 0.7188. Min Range: -0.7188

Max Act: 0.5749. Min Act: -0.0001

Data Index: 1044879 (C4 (Web Text))

Max Activating Token Index: 167

Text #13

Max Range: 0.7188. Min Range: -0.7188

Max Act: 0.5822. Min Act: -0.0000

Data Index: 32080 (C4 (Web Text))

Max Activating Token Index: 102

Text #14

Max Range: 0.7188. Min Range: -0.7188

Max Act: 0.5804. Min Act: -0.0000

Data Index: 240585 (C4 (Web Text))

Max Activating Token Index: 424

Text #15

Max Range: 0.7188. Min Range: -0.7188

Max Act: 0.5790. Min Act: -0.0000

Data Index: 865022 (C4 (Web Text))

Max Activating Token Index: 493

Text #16

Max Range: 0.7188. Min Range: -0.7188

Max Act: 0.5792. Min Act: -0.0000

Data Index: 636031 (C4 (Web Text))

Max Activating Token Index: 200

Text #17

Max Range: 0.7188. Min Range: -0.7188

Max Act: 0.5783. Min Act: -0.0000

Data Index: 374181 (C4 (Web Text))

Max Activating Token Index: 684

Text #18

Max Range: 0.7188. Min Range: -0.7188

Max Act: 0.5735. Min Act: -0.0001

Data Index: 262334 (C4 (Web Text))

Max Activating Token Index: 135

Text #19

Max Range: 0.7188. Min Range: -0.7188

Max Act: 0.5729. Min Act: -0.0001

Data Index: 96365 (C4 (Web Text))

Max Activating Token Index: 145