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

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

Neuron 698 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9179. Min Range: -0.9179

Max Act: 0.8931. Min Act: -0.0001

Data Index: 1513929 (Python Code)

Max Activating Token Index: 299

Text #1

Max Range: 0.9179. Min Range: -0.9179

Max Act: 0.9179. Min Act: -0.0001

Data Index: 1408644 (Python Code)

Max Activating Token Index: 338

Text #2

Max Range: 0.9179. Min Range: -0.9179

Max Act: 0.7458. Min Act: -0.0000

Data Index: 1474389 (Python Code)

Max Activating Token Index: 475

Text #3

Max Range: 0.9179. Min Range: -0.9179

Max Act: 0.7022. Min Act: -0.0001

Data Index: 1514447 (Python Code)

Max Activating Token Index: 986

Text #4

Max Range: 0.9179. Min Range: -0.9179

Max Act: 0.7412. Min Act: -0.0001

Data Index: 1640532 (Python Code)

Max Activating Token Index: 327

Text #5

Max Range: 0.9179. Min Range: -0.9179

Max Act: 0.6623. Min Act: -0.0001

Data Index: 1644292 (Python Code)

Max Activating Token Index: 376

Text #6

Max Range: 0.9179. Min Range: -0.9179

Max Act: 0.6894. Min Act: -0.0001

Data Index: 1564472 (Python Code)

Max Activating Token Index: 434

Text #7

Max Range: 0.9179. Min Range: -0.9179

Max Act: 0.6771. Min Act: -0.0001

Data Index: 1593712 (Python Code)

Max Activating Token Index: 50

Text #8

Max Range: 0.9179. Min Range: -0.9179

Max Act: 0.6884. Min Act: -0.0001

Data Index: 1527620 (Python Code)

Max Activating Token Index: 564

Text #9

Max Range: 0.9179. Min Range: -0.9179

Max Act: 0.6755. Min Act: -0.0001

Data Index: 1451210 (Python Code)

Max Activating Token Index: 546

Text #10

Max Range: 0.9179. Min Range: -0.9179

Max Act: 0.6531. Min Act: -0.0001

Data Index: 1655257 (Python Code)

Max Activating Token Index: 910

Text #11

Max Range: 0.9179. Min Range: -0.9179

Max Act: 0.6430. Min Act: -0.0001

Data Index: 1531085 (Python Code)

Max Activating Token Index: 416

Text #12

Max Range: 0.9179. Min Range: -0.9179

Max Act: 0.6402. Min Act: -0.0000

Data Index: 1488415 (Python Code)

Max Activating Token Index: 324

Text #13

Max Range: 0.9179. Min Range: -0.9179

Max Act: 0.6596. Min Act: -0.0001

Data Index: 1431266 (Python Code)

Max Activating Token Index: 922

Text #14

Max Range: 0.9179. Min Range: -0.9179

Max Act: 0.6142. Min Act: -0.0001

Data Index: 1579351 (Python Code)

Max Activating Token Index: 292

Text #15

Max Range: 0.9179. Min Range: -0.9179

Max Act: 0.6258. Min Act: -0.0001

Data Index: 1544360 (Python Code)

Max Activating Token Index: 464

Text #16

Max Range: 0.9179. Min Range: -0.9179

Max Act: 0.6088. Min Act: -0.0001

Data Index: 1443537 (Python Code)

Max Activating Token Index: 270

Text #17

Max Range: 0.9179. Min Range: -0.9179

Max Act: 0.6269. Min Act: -0.0001

Data Index: 1379608 (Python Code)

Max Activating Token Index: 1017

Text #18

Max Range: 0.9179. Min Range: -0.9179

Max Act: 0.6207. Min Act: -0.0001

Data Index: 1642068 (Python Code)

Max Activating Token Index: 775

Text #19

Max Range: 0.9179. Min Range: -0.9179

Max Act: 0.6438. Min Act: -0.0001

Data Index: 1535099 (Python Code)

Max Activating Token Index: 324