Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 988 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.5372. Min Range: -0.5372

Max Act: 0.5372. Min Act: -0.0003

Data Index: 1486334 (Python Code)

Max Activating Token Index: 847

Text #1

Max Range: 0.5372. Min Range: -0.5372

Max Act: 0.4186. Min Act: -0.0003

Data Index: 1509306 (Python Code)

Max Activating Token Index: 967

Text #2

Max Range: 0.5372. Min Range: -0.5372

Max Act: 0.4590. Min Act: -0.0003

Data Index: 1430047 (Python Code)

Max Activating Token Index: 125

Text #3

Max Range: 0.5372. Min Range: -0.5372

Max Act: 0.4378. Min Act: -0.0003

Data Index: 1580150 (Python Code)

Max Activating Token Index: 128

Text #4

Max Range: 0.5372. Min Range: -0.5372

Max Act: 0.4192. Min Act: -0.0003

Data Index: 1413771 (Python Code)

Max Activating Token Index: 509

Text #5

Max Range: 0.5372. Min Range: -0.5372

Max Act: 0.4197. Min Act: -0.0003

Data Index: 1367993 (Python Code)

Max Activating Token Index: 1009

Text #6

Max Range: 0.5372. Min Range: -0.5372

Max Act: 0.4111. Min Act: -0.0003

Data Index: 1551245 (Python Code)

Max Activating Token Index: 259

Text #7

Max Range: 0.5372. Min Range: -0.5372

Max Act: 0.4327. Min Act: -0.0003

Data Index: 1497238 (Python Code)

Max Activating Token Index: 995

Text #8

Max Range: 0.5372. Min Range: -0.5372

Max Act: 0.4015. Min Act: -0.0003

Data Index: 1503195 (Python Code)

Max Activating Token Index: 61

Text #9

Max Range: 0.5372. Min Range: -0.5372

Max Act: 0.4200. Min Act: -0.0003

Data Index: 1466225 (Python Code)

Max Activating Token Index: 854

Text #10

Max Range: 0.5372. Min Range: -0.5372

Max Act: 0.3970. Min Act: -0.0003

Data Index: 1376305 (Python Code)

Max Activating Token Index: 519

Text #11

Max Range: 0.5372. Min Range: -0.5372

Max Act: 0.4079. Min Act: -0.0003

Data Index: 1364160 (Python Code)

Max Activating Token Index: 231

Text #12

Max Range: 0.5372. Min Range: -0.5372

Max Act: 0.4029. Min Act: -0.0003

Data Index: 1610253 (Python Code)

Max Activating Token Index: 911

Text #13

Max Range: 0.5372. Min Range: -0.5372

Max Act: 0.4031. Min Act: -0.0003

Data Index: 1538023 (Python Code)

Max Activating Token Index: 940

Text #14

Max Range: 0.5372. Min Range: -0.5372

Max Act: 0.4135. Min Act: -0.0003

Data Index: 1393546 (Python Code)

Max Activating Token Index: 693

Text #15

Max Range: 0.5372. Min Range: -0.5372

Max Act: 0.4194. Min Act: -0.0003

Data Index: 1622761 (Python Code)

Max Activating Token Index: 119

Text #16

Max Range: 0.5372. Min Range: -0.5372

Max Act: 0.4014. Min Act: -0.0003

Data Index: 1631076 (Python Code)

Max Activating Token Index: 860

Text #17

Max Range: 0.5372. Min Range: -0.5372

Max Act: 0.4010. Min Act: -0.0003

Data Index: 1446651 (Python Code)

Max Activating Token Index: 30

Text #18

Max Range: 0.5372. Min Range: -0.5372

Max Act: 0.3840. Min Act: -0.0003

Data Index: 1554510 (Python Code)

Max Activating Token Index: 999

Text #19

Max Range: 0.5372. Min Range: -0.5372

Max Act: 0.3815. Min Act: -0.0003

Data Index: 1570680 (Python Code)

Max Activating Token Index: 203