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

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

Neuron 4007 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7275. Min Range: -0.7275

Max Act: 0.7275. Min Act: -0.0000

Data Index: 1593271 (Python Code)

Max Activating Token Index: 439

Text #1

Max Range: 0.7275. Min Range: -0.7275

Max Act: 0.6931. Min Act: -0.0001

Data Index: 1591732 (Python Code)

Max Activating Token Index: 220

Text #2

Max Range: 0.7275. Min Range: -0.7275

Max Act: 0.6987. Min Act: -0.0000

Data Index: 1395985 (Python Code)

Max Activating Token Index: 659

Text #3

Max Range: 0.7275. Min Range: -0.7275

Max Act: 0.6921. Min Act: -0.0001

Data Index: 1639324 (Python Code)

Max Activating Token Index: 263

Text #4

Max Range: 0.7275. Min Range: -0.7275

Max Act: 0.7132. Min Act: -0.0000

Data Index: 1583073 (Python Code)

Max Activating Token Index: 771

Text #5

Max Range: 0.7275. Min Range: -0.7275

Max Act: 0.6944. Min Act: -0.0000

Data Index: 1612405 (Python Code)

Max Activating Token Index: 937

Text #6

Max Range: 0.7275. Min Range: -0.7275

Max Act: 0.6772. Min Act: -0.0001

Data Index: 1476326 (Python Code)

Max Activating Token Index: 325

Text #7

Max Range: 0.7275. Min Range: -0.7275

Max Act: 0.6470. Min Act: -0.0000

Data Index: 1425680 (Python Code)

Max Activating Token Index: 871

Text #8

Max Range: 0.7275. Min Range: -0.7275

Max Act: 0.6218. Min Act: -0.0000

Data Index: 1568657 (Python Code)

Max Activating Token Index: 61

Text #9

Max Range: 0.7275. Min Range: -0.7275

Max Act: 0.6113. Min Act: -0.0001

Data Index: 1654548 (Python Code)

Max Activating Token Index: 470

Text #10

Max Range: 0.7275. Min Range: -0.7275

Max Act: 0.5625. Min Act: -0.0001

Data Index: 1614851 (Python Code)

Max Activating Token Index: 881

Text #11

Max Range: 0.7275. Min Range: -0.7275

Max Act: 0.5734. Min Act: -0.0000

Data Index: 1582848 (Python Code)

Max Activating Token Index: 25

Text #12

Max Range: 0.7275. Min Range: -0.7275

Max Act: 0.5904. Min Act: -0.0000

Data Index: 1417222 (Python Code)

Max Activating Token Index: 997

Text #13

Max Range: 0.7275. Min Range: -0.7275

Max Act: 0.5683. Min Act: -0.0001

Data Index: 1374147 (Python Code)

Max Activating Token Index: 73

Text #14

Max Range: 0.7275. Min Range: -0.7275

Max Act: 0.5633. Min Act: -0.0001

Data Index: 1386901 (Python Code)

Max Activating Token Index: 81

Text #15

Max Range: 0.7275. Min Range: -0.7275

Max Act: 0.5626. Min Act: -0.0000

Data Index: 1530562 (Python Code)

Max Activating Token Index: 423

Text #16

Max Range: 0.7275. Min Range: -0.7275

Max Act: 0.5569. Min Act: -0.0001

Data Index: 776786 (C4 (Web Text))

Max Activating Token Index: 524

Text #17

Max Range: 0.7275. Min Range: -0.7275

Max Act: 0.6123. Min Act: -0.0000

Data Index: 1461603 (Python Code)

Max Activating Token Index: 57

Text #18

Max Range: 0.7275. Min Range: -0.7275

Max Act: 0.5875. Min Act: -0.0000

Data Index: 1633617 (Python Code)

Max Activating Token Index: 322

Text #19

Max Range: 0.7275. Min Range: -0.7275

Max Act: 0.5851. Min Act: -0.0000

Data Index: 1603797 (Python Code)

Max Activating Token Index: 668