Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5864 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.3512. Min Range: -0.3512

Max Act: 0.3512. Min Act: -0.0000

Data Index: 1476859 (Python Code)

Max Activating Token Index: 1001

Text #1

Max Range: 0.3512. Min Range: -0.3512

Max Act: 0.3121. Min Act: -0.0000

Data Index: 1368614 (Python Code)

Max Activating Token Index: 498

Text #2

Max Range: 0.3512. Min Range: -0.3512

Max Act: 0.3287. Min Act: -0.0000

Data Index: 1522001 (Python Code)

Max Activating Token Index: 937

Text #3

Max Range: 0.3512. Min Range: -0.3512

Max Act: 0.2742. Min Act: -0.0000

Data Index: 460707 (C4 (Web Text))

Max Activating Token Index: 385

Text #4

Max Range: 0.3512. Min Range: -0.3512

Max Act: 0.2896. Min Act: -0.0000

Data Index: 1151104 (C4 (Web Text))

Max Activating Token Index: 403

Text #5

Max Range: 0.3512. Min Range: -0.3512

Max Act: 0.2712. Min Act: -0.0000

Data Index: 377983 (C4 (Web Text))

Max Activating Token Index: 846

Text #6

Max Range: 0.3512. Min Range: -0.3512

Max Act: 0.2330. Min Act: -0.0000

Data Index: 1621786 (Python Code)

Max Activating Token Index: 929

Text #7

Max Range: 0.3512. Min Range: -0.3512

Max Act: 0.2268. Min Act: -0.0000

Data Index: 1325492 (C4 (Web Text))

Max Activating Token Index: 835

Text #8

Max Range: 0.3512. Min Range: -0.3512

Max Act: 0.2287. Min Act: -0.0000

Data Index: 662729 (C4 (Web Text))

Max Activating Token Index: 386

Text #9

Max Range: 0.3512. Min Range: -0.3512

Max Act: 0.2358. Min Act: -0.0000

Data Index: 1514042 (Python Code)

Max Activating Token Index: 292

Text #10

Max Range: 0.3512. Min Range: -0.3512

Max Act: 0.2286. Min Act: -0.0000

Data Index: 1094863 (C4 (Web Text))

Max Activating Token Index: 560

Text #11

Max Range: 0.3512. Min Range: -0.3512

Max Act: 0.2196. Min Act: -0.0000

Data Index: 1541645 (Python Code)

Max Activating Token Index: 487

Text #12

Max Range: 0.3512. Min Range: -0.3512

Max Act: 0.2095. Min Act: -0.0000

Data Index: 528893 (C4 (Web Text))

Max Activating Token Index: 794

Text #13

Max Range: 0.3512. Min Range: -0.3512

Max Act: 0.2046. Min Act: -0.0000

Data Index: 828016 (C4 (Web Text))

Max Activating Token Index: 566

Text #14

Max Range: 0.3512. Min Range: -0.3512

Max Act: 0.2159. Min Act: -0.0000

Data Index: 1172505 (C4 (Web Text))

Max Activating Token Index: 477

Text #15

Max Range: 0.3512. Min Range: -0.3512

Max Act: 0.2110. Min Act: -0.0000

Data Index: 1367554 (Python Code)

Max Activating Token Index: 338

Text #16

Max Range: 0.3512. Min Range: -0.3512

Max Act: 0.1943. Min Act: -0.0000

Data Index: 1461098 (Python Code)

Max Activating Token Index: 536

Text #17

Max Range: 0.3512. Min Range: -0.3512

Max Act: 0.1906. Min Act: -0.0000

Data Index: 653161 (C4 (Web Text))

Max Activating Token Index: 462

Text #18

Max Range: 0.3512. Min Range: -0.3512

Max Act: 0.1944. Min Act: -0.0000

Data Index: 895561 (C4 (Web Text))

Max Activating Token Index: 333

Text #19

Max Range: 0.3512. Min Range: -0.3512

Max Act: 0.2058. Min Act: -0.0000

Data Index: 334390 (C4 (Web Text))

Max Activating Token Index: 515