Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 662 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.8140. Min Range: -0.8140

Max Act: 0.8140. Min Act: -0.0000

Data Index: 1258322 (C4 (Web Text))

Max Activating Token Index: 838

Text #1

Max Range: 0.8140. Min Range: -0.8140

Max Act: 0.6163. Min Act: -0.0000

Data Index: 104165 (C4 (Web Text))

Max Activating Token Index: 616

Text #2

Max Range: 0.8140. Min Range: -0.8140

Max Act: 0.5516. Min Act: -0.0000

Data Index: 650433 (C4 (Web Text))

Max Activating Token Index: 1012

Text #3

Max Range: 0.8140. Min Range: -0.8140

Max Act: 0.5336. Min Act: -0.0000

Data Index: 942256 (C4 (Web Text))

Max Activating Token Index: 535

Text #4

Max Range: 0.8140. Min Range: -0.8140

Max Act: 0.4917. Min Act: -0.0000

Data Index: 78778 (C4 (Web Text))

Max Activating Token Index: 937

Text #5

Max Range: 0.8140. Min Range: -0.8140

Max Act: 0.4671. Min Act: -0.0000

Data Index: 770636 (C4 (Web Text))

Max Activating Token Index: 484

Text #6

Max Range: 0.8140. Min Range: -0.8140

Max Act: 0.4692. Min Act: -0.0000

Data Index: 772149 (C4 (Web Text))

Max Activating Token Index: 767

Text #7

Max Range: 0.8140. Min Range: -0.8140

Max Act: 0.4290. Min Act: -0.0000

Data Index: 1450080 (Python Code)

Max Activating Token Index: 491

Text #8

Max Range: 0.8140. Min Range: -0.8140

Max Act: 0.4227. Min Act: -0.0000

Data Index: 1438679 (Python Code)

Max Activating Token Index: 402

Text #9

Max Range: 0.8140. Min Range: -0.8140

Max Act: 0.4362. Min Act: -0.0000

Data Index: 351785 (C4 (Web Text))

Max Activating Token Index: 151

Text #10

Max Range: 0.8140. Min Range: -0.8140

Max Act: 0.4451. Min Act: -0.0000

Data Index: 795698 (C4 (Web Text))

Max Activating Token Index: 818

Text #11

Max Range: 0.8140. Min Range: -0.8140

Max Act: 0.4178. Min Act: -0.0000

Data Index: 1121480 (C4 (Web Text))

Max Activating Token Index: 589

Text #12

Max Range: 0.8140. Min Range: -0.8140

Max Act: 0.4649. Min Act: -0.0000

Data Index: 1620177 (Python Code)

Max Activating Token Index: 634

Text #13

Max Range: 0.8140. Min Range: -0.8140

Max Act: 0.4300. Min Act: -0.0000

Data Index: 542666 (C4 (Web Text))

Max Activating Token Index: 442

Text #14

Max Range: 0.8140. Min Range: -0.8140

Max Act: 0.4180. Min Act: -0.0000

Data Index: 1044436 (C4 (Web Text))

Max Activating Token Index: 740

Text #15

Max Range: 0.8140. Min Range: -0.8140

Max Act: 0.4165. Min Act: -0.0000

Data Index: 594262 (C4 (Web Text))

Max Activating Token Index: 186

Text #16

Max Range: 0.8140. Min Range: -0.8140

Max Act: 0.3928. Min Act: -0.0000

Data Index: 658477 (C4 (Web Text))

Max Activating Token Index: 412

Text #17

Max Range: 0.8140. Min Range: -0.8140

Max Act: 0.3955. Min Act: -0.0000

Data Index: 165053 (C4 (Web Text))

Max Activating Token Index: 380

Text #18

Max Range: 0.8140. Min Range: -0.8140

Max Act: 0.3941. Min Act: -0.0000

Data Index: 1240313 (C4 (Web Text))

Max Activating Token Index: 556

Text #19

Max Range: 0.8140. Min Range: -0.8140

Max Act: 0.3869. Min Act: -0.0000

Data Index: 134154 (C4 (Web Text))

Max Activating Token Index: 344