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

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

Neuron 2224 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6965. Min Range: -0.6965

Max Act: 0.6853. Min Act: -0.0001

Data Index: 1082883 (C4 (Web Text))

Max Activating Token Index: 149

Text #1

Max Range: 0.6965. Min Range: -0.6965

Max Act: 0.6840. Min Act: -0.0001

Data Index: 94980 (C4 (Web Text))

Max Activating Token Index: 514

Text #2

Max Range: 0.6965. Min Range: -0.6965

Max Act: 0.6965. Min Act: -0.0001

Data Index: 1160811 (C4 (Web Text))

Max Activating Token Index: 81

Text #3

Max Range: 0.6965. Min Range: -0.6965

Max Act: 0.6719. Min Act: -0.0001

Data Index: 881169 (C4 (Web Text))

Max Activating Token Index: 718

Text #4

Max Range: 0.6965. Min Range: -0.6965

Max Act: 0.6767. Min Act: -0.0001

Data Index: 464634 (C4 (Web Text))

Max Activating Token Index: 261

Text #5

Max Range: 0.6965. Min Range: -0.6965

Max Act: 0.6542. Min Act: -0.0001

Data Index: 625551 (C4 (Web Text))

Max Activating Token Index: 63

Text #6

Max Range: 0.6965. Min Range: -0.6965

Max Act: 0.6715. Min Act: -0.0001

Data Index: 1207359 (C4 (Web Text))

Max Activating Token Index: 570

Text #7

Max Range: 0.6965. Min Range: -0.6965

Max Act: 0.6483. Min Act: -0.0001

Data Index: 221918 (C4 (Web Text))

Max Activating Token Index: 705

Text #8

Max Range: 0.6965. Min Range: -0.6965

Max Act: 0.6483. Min Act: -0.0001

Data Index: 411424 (C4 (Web Text))

Max Activating Token Index: 99

Text #9

Max Range: 0.6965. Min Range: -0.6965

Max Act: 0.6756. Min Act: -0.0001

Data Index: 112995 (C4 (Web Text))

Max Activating Token Index: 593

Text #10

Max Range: 0.6965. Min Range: -0.6965

Max Act: 0.6277. Min Act: -0.0001

Data Index: 524683 (C4 (Web Text))

Max Activating Token Index: 425

Text #11

Max Range: 0.6965. Min Range: -0.6965

Max Act: 0.6278. Min Act: -0.0001

Data Index: 334722 (C4 (Web Text))

Max Activating Token Index: 318

Text #12

Max Range: 0.6965. Min Range: -0.6965

Max Act: 0.6428. Min Act: -0.0001

Data Index: 299919 (C4 (Web Text))

Max Activating Token Index: 313

Text #13

Max Range: 0.6965. Min Range: -0.6965

Max Act: 0.6351. Min Act: -0.0001

Data Index: 1127748 (C4 (Web Text))

Max Activating Token Index: 26

Text #14

Max Range: 0.6965. Min Range: -0.6965

Max Act: 0.6156. Min Act: -0.0001

Data Index: 274120 (C4 (Web Text))

Max Activating Token Index: 423

Text #15

Max Range: 0.6965. Min Range: -0.6965

Max Act: 0.6101. Min Act: -0.0001

Data Index: 398601 (C4 (Web Text))

Max Activating Token Index: 611

Text #16

Max Range: 0.6965. Min Range: -0.6965

Max Act: 0.6232. Min Act: -0.0001

Data Index: 1315555 (C4 (Web Text))

Max Activating Token Index: 948

Text #17

Max Range: 0.6965. Min Range: -0.6965

Max Act: 0.6454. Min Act: -0.0001

Data Index: 274865 (C4 (Web Text))

Max Activating Token Index: 784

Text #18

Max Range: 0.6965. Min Range: -0.6965

Max Act: 0.6003. Min Act: -0.0001

Data Index: 671121 (C4 (Web Text))

Max Activating Token Index: 611

Text #19

Max Range: 0.6965. Min Range: -0.6965

Max Act: 0.5594. Min Act: -0.0001

Data Index: 120306 (C4 (Web Text))

Max Activating Token Index: 961