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

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

Neuron 1710 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7884. Min Range: -1.7884

Max Act: 1.7884. Min Act: -0.0000

Data Index: 1447441 (Python Code)

Max Activating Token Index: 296

Text #1

Max Range: 1.7884. Min Range: -1.7884

Max Act: 1.6629. Min Act: -0.0000

Data Index: 1514019 (Python Code)

Max Activating Token Index: 300

Text #2

Max Range: 1.7884. Min Range: -1.7884

Max Act: 1.6715. Min Act: -0.0000

Data Index: 1517552 (Python Code)

Max Activating Token Index: 321

Text #3

Max Range: 1.7884. Min Range: -1.7884

Max Act: 1.5557. Min Act: -0.0000

Data Index: 1444512 (Python Code)

Max Activating Token Index: 244

Text #4

Max Range: 1.7884. Min Range: -1.7884

Max Act: 1.4508. Min Act: -0.0000

Data Index: 1381310 (Python Code)

Max Activating Token Index: 208

Text #5

Max Range: 1.7884. Min Range: -1.7884

Max Act: 1.5239. Min Act: -0.0000

Data Index: 1559221 (Python Code)

Max Activating Token Index: 147

Text #6

Max Range: 1.7884. Min Range: -1.7884

Max Act: 1.4757. Min Act: -0.0000

Data Index: 1600834 (Python Code)

Max Activating Token Index: 43

Text #7

Max Range: 1.7884. Min Range: -1.7884

Max Act: 1.4359. Min Act: -0.0000

Data Index: 1383700 (Python Code)

Max Activating Token Index: 696

Text #8

Max Range: 1.7884. Min Range: -1.7884

Max Act: 1.4579. Min Act: -0.0000

Data Index: 1600289 (Python Code)

Max Activating Token Index: 250

Text #9

Max Range: 1.7884. Min Range: -1.7884

Max Act: 1.4768. Min Act: -0.0000

Data Index: 1505233 (Python Code)

Max Activating Token Index: 124

Text #10

Max Range: 1.7884. Min Range: -1.7884

Max Act: 1.3954. Min Act: -0.0000

Data Index: 1390555 (Python Code)

Max Activating Token Index: 529

Text #11

Max Range: 1.7884. Min Range: -1.7884

Max Act: 1.3448. Min Act: -0.0000

Data Index: 1535187 (Python Code)

Max Activating Token Index: 501

Text #12

Max Range: 1.7884. Min Range: -1.7884

Max Act: 1.3235. Min Act: -0.0000

Data Index: 1542913 (Python Code)

Max Activating Token Index: 716

Text #13

Max Range: 1.7884. Min Range: -1.7884

Max Act: 1.3696. Min Act: -0.0000

Data Index: 1559882 (Python Code)

Max Activating Token Index: 223

Text #14

Max Range: 1.7884. Min Range: -1.7884

Max Act: 1.3436. Min Act: -0.0000

Data Index: 1476839 (Python Code)

Max Activating Token Index: 960

Text #15

Max Range: 1.7884. Min Range: -1.7884

Max Act: 1.2839. Min Act: -0.0000

Data Index: 1395756 (Python Code)

Max Activating Token Index: 243

Text #16

Max Range: 1.7884. Min Range: -1.7884

Max Act: 1.3215. Min Act: -0.0000

Data Index: 1511487 (Python Code)

Max Activating Token Index: 579

Text #17

Max Range: 1.7884. Min Range: -1.7884

Max Act: 1.2550. Min Act: -0.0000

Data Index: 1531113 (Python Code)

Max Activating Token Index: 177

Text #18

Max Range: 1.7884. Min Range: -1.7884

Max Act: 1.4429. Min Act: -0.0000

Data Index: 1560063 (Python Code)

Max Activating Token Index: 167

Text #19

Max Range: 1.7884. Min Range: -1.7884

Max Act: 1.3414. Min Act: -0.0000

Data Index: 1523397 (Python Code)

Max Activating Token Index: 833