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

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

Neuron 239 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: 0.7280. Min Range: -0.7280

Max Act: 0.7001. Min Act: -0.0001

Data Index: 1506163 (Python Code)

Max Activating Token Index: 690

Text #1

Max Range: 0.7280. Min Range: -0.7280

Max Act: 0.7280. Min Act: -0.0001

Data Index: 1546701 (Python Code)

Max Activating Token Index: 993

Text #2

Max Range: 0.7280. Min Range: -0.7280

Max Act: 0.6766. Min Act: -0.0001

Data Index: 1604376 (Python Code)

Max Activating Token Index: 715

Text #3

Max Range: 0.7280. Min Range: -0.7280

Max Act: 0.6753. Min Act: -0.0001

Data Index: 1382755 (Python Code)

Max Activating Token Index: 1006

Text #4

Max Range: 0.7280. Min Range: -0.7280

Max Act: 0.7025. Min Act: -0.0001

Data Index: 1523095 (Python Code)

Max Activating Token Index: 772

Text #5

Max Range: 0.7280. Min Range: -0.7280

Max Act: 0.6478. Min Act: -0.0001

Data Index: 1633786 (Python Code)

Max Activating Token Index: 950

Text #6

Max Range: 0.7280. Min Range: -0.7280

Max Act: 0.6414. Min Act: -0.0001

Data Index: 1485315 (Python Code)

Max Activating Token Index: 392

Text #7

Max Range: 0.7280. Min Range: -0.7280

Max Act: 0.5976. Min Act: -0.0001

Data Index: 1484748 (Python Code)

Max Activating Token Index: 205

Text #8

Max Range: 0.7280. Min Range: -0.7280

Max Act: 0.6449. Min Act: -0.0001

Data Index: 1651336 (Python Code)

Max Activating Token Index: 902

Text #9

Max Range: 0.7280. Min Range: -0.7280

Max Act: 0.6180. Min Act: -0.0001

Data Index: 1631548 (Python Code)

Max Activating Token Index: 609

Text #10

Max Range: 0.7280. Min Range: -0.7280

Max Act: 0.6160. Min Act: -0.0001

Data Index: 1513325 (Python Code)

Max Activating Token Index: 325

Text #11

Max Range: 0.7280. Min Range: -0.7280

Max Act: 0.5618. Min Act: -0.0001

Data Index: 1364530 (Python Code)

Max Activating Token Index: 271

Text #12

Max Range: 0.7280. Min Range: -0.7280

Max Act: 0.6318. Min Act: -0.0001

Data Index: 1527934 (Python Code)

Max Activating Token Index: 209

Text #13

Max Range: 0.7280. Min Range: -0.7280

Max Act: 0.5977. Min Act: -0.0001

Data Index: 1625917 (Python Code)

Max Activating Token Index: 652

Text #14

Max Range: 0.7280. Min Range: -0.7280

Max Act: 0.5793. Min Act: -0.0001

Data Index: 1556914 (Python Code)

Max Activating Token Index: 585

Text #15

Max Range: 0.7280. Min Range: -0.7280

Max Act: 0.5757. Min Act: -0.0001

Data Index: 1450092 (Python Code)

Max Activating Token Index: 665

Text #16

Max Range: 0.7280. Min Range: -0.7280

Max Act: 0.5492. Min Act: -0.0001

Data Index: 1613967 (Python Code)

Max Activating Token Index: 138

Text #17

Max Range: 0.7280. Min Range: -0.7280

Max Act: 0.5341. Min Act: -0.0001

Data Index: 1647926 (Python Code)

Max Activating Token Index: 409

Text #18

Max Range: 0.7280. Min Range: -0.7280

Max Act: 0.5489. Min Act: -0.0000

Data Index: 1400321 (Python Code)

Max Activating Token Index: 1018

Text #19

Max Range: 0.7280. Min Range: -0.7280

Max Act: 0.4973. Min Act: -0.0001

Data Index: 1599993 (Python Code)

Max Activating Token Index: 976