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

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

Neuron 3071 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7437. Min Range: -0.7437

Max Act: 0.7437. Min Act: -0.0001

Data Index: 1388891 (Python Code)

Max Activating Token Index: 964

Text #1

Max Range: 0.7437. Min Range: -0.7437

Max Act: 0.6795. Min Act: 0.0001

Data Index: 1581474 (Python Code)

Max Activating Token Index: 362

Text #2

Max Range: 0.7437. Min Range: -0.7437

Max Act: 0.7229. Min Act: -0.0000

Data Index: 1635809 (Python Code)

Max Activating Token Index: 32

Text #3

Max Range: 0.7437. Min Range: -0.7437

Max Act: 0.6757. Min Act: -0.0000

Data Index: 1425560 (Python Code)

Max Activating Token Index: 681

Text #4

Max Range: 0.7437. Min Range: -0.7437

Max Act: 0.6693. Min Act: -0.0001

Data Index: 1601862 (Python Code)

Max Activating Token Index: 460

Text #5

Max Range: 0.7437. Min Range: -0.7437

Max Act: 0.6309. Min Act: -0.0000

Data Index: 1528849 (Python Code)

Max Activating Token Index: 936

Text #6

Max Range: 0.7437. Min Range: -0.7437

Max Act: 0.6555. Min Act: -0.0000

Data Index: 1622078 (Python Code)

Max Activating Token Index: 36

Text #7

Max Range: 0.7437. Min Range: -0.7437

Max Act: 0.6727. Min Act: 0.0001

Data Index: 1374953 (Python Code)

Max Activating Token Index: 176

Text #8

Max Range: 0.7437. Min Range: -0.7437

Max Act: 0.6694. Min Act: -0.0000

Data Index: 1496187 (Python Code)

Max Activating Token Index: 983

Text #9

Max Range: 0.7437. Min Range: -0.7437

Max Act: 0.6232. Min Act: -0.0000

Data Index: 1391349 (Python Code)

Max Activating Token Index: 657

Text #10

Max Range: 0.7437. Min Range: -0.7437

Max Act: 0.6742. Min Act: -0.0000

Data Index: 1455516 (Python Code)

Max Activating Token Index: 856

Text #11

Max Range: 0.7437. Min Range: -0.7437

Max Act: 0.6292. Min Act: 0.0000

Data Index: 1524281 (Python Code)

Max Activating Token Index: 57

Text #12

Max Range: 0.7437. Min Range: -0.7437

Max Act: 0.6543. Min Act: -0.0000

Data Index: 1510539 (Python Code)

Max Activating Token Index: 280

Text #13

Max Range: 0.7437. Min Range: -0.7437

Max Act: 0.6198. Min Act: 0.0001

Data Index: 1599085 (Python Code)

Max Activating Token Index: 404

Text #14

Max Range: 0.7437. Min Range: -0.7437

Max Act: 0.5995. Min Act: -0.0000

Data Index: 1486986 (Python Code)

Max Activating Token Index: 543

Text #15

Max Range: 0.7437. Min Range: -0.7437

Max Act: 0.5872. Min Act: -0.0000

Data Index: 1456118 (Python Code)

Max Activating Token Index: 317

Text #16

Max Range: 0.7437. Min Range: -0.7437

Max Act: 0.6039. Min Act: 0.0001

Data Index: 1373644 (Python Code)

Max Activating Token Index: 523

Text #17

Max Range: 0.7437. Min Range: -0.7437

Max Act: 0.5934. Min Act: -0.0000

Data Index: 1410174 (Python Code)

Max Activating Token Index: 543

Text #18

Max Range: 0.7437. Min Range: -0.7437

Max Act: 0.6360. Min Act: -0.0000

Data Index: 1406843 (Python Code)

Max Activating Token Index: 475

Text #19

Max Range: 0.7437. Min Range: -0.7437

Max Act: 0.6095. Min Act: -0.0000

Data Index: 1597831 (Python Code)

Max Activating Token Index: 796