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

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

Neuron 5743 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: 1.6928. Min Range: -1.6928

Max Act: 1.6928. Min Act: -0.0001

Data Index: 1526504 (Python Code)

Max Activating Token Index: 620

Text #1

Max Range: 1.6928. Min Range: -1.6928

Max Act: 1.6041. Min Act: -0.0001

Data Index: 1572481 (Python Code)

Max Activating Token Index: 731

Text #2

Max Range: 1.6928. Min Range: -1.6928

Max Act: 1.5018. Min Act: -0.0001

Data Index: 1369429 (Python Code)

Max Activating Token Index: 453

Text #3

Max Range: 1.6928. Min Range: -1.6928

Max Act: 1.4487. Min Act: -0.0001

Data Index: 1639691 (Python Code)

Max Activating Token Index: 937

Text #4

Max Range: 1.6928. Min Range: -1.6928

Max Act: 1.3784. Min Act: -0.0001

Data Index: 1618266 (Python Code)

Max Activating Token Index: 210

Text #5

Max Range: 1.6928. Min Range: -1.6928

Max Act: 1.3674. Min Act: -0.0000

Data Index: 1543448 (Python Code)

Max Activating Token Index: 490

Text #6

Max Range: 1.6928. Min Range: -1.6928

Max Act: 1.3655. Min Act: -0.0001

Data Index: 1617562 (Python Code)

Max Activating Token Index: 386

Text #7

Max Range: 1.6928. Min Range: -1.6928

Max Act: 1.2762. Min Act: -0.0001

Data Index: 1467616 (Python Code)

Max Activating Token Index: 735

Text #8

Max Range: 1.6928. Min Range: -1.6928

Max Act: 1.3619. Min Act: -0.0001

Data Index: 1424760 (Python Code)

Max Activating Token Index: 190

Text #9

Max Range: 1.6928. Min Range: -1.6928

Max Act: 1.3537. Min Act: -0.0000

Data Index: 1398015 (Python Code)

Max Activating Token Index: 402

Text #10

Max Range: 1.6928. Min Range: -1.6928

Max Act: 1.3079. Min Act: -0.0000

Data Index: 1399708 (Python Code)

Max Activating Token Index: 638

Text #11

Max Range: 1.6928. Min Range: -1.6928

Max Act: 1.3768. Min Act: -0.0001

Data Index: 1407774 (Python Code)

Max Activating Token Index: 620

Text #12

Max Range: 1.6928. Min Range: -1.6928

Max Act: 1.3550. Min Act: -0.0000

Data Index: 1536847 (Python Code)

Max Activating Token Index: 862

Text #13

Max Range: 1.6928. Min Range: -1.6928

Max Act: 1.2222. Min Act: -0.0000

Data Index: 1519036 (Python Code)

Max Activating Token Index: 173

Text #14

Max Range: 1.6928. Min Range: -1.6928

Max Act: 1.3023. Min Act: -0.0001

Data Index: 1509652 (Python Code)

Max Activating Token Index: 114

Text #15

Max Range: 1.6928. Min Range: -1.6928

Max Act: 1.2583. Min Act: -0.0000

Data Index: 1480642 (Python Code)

Max Activating Token Index: 237

Text #16

Max Range: 1.6928. Min Range: -1.6928

Max Act: 1.1863. Min Act: -0.0001

Data Index: 1493703 (Python Code)

Max Activating Token Index: 213

Text #17

Max Range: 1.6928. Min Range: -1.6928

Max Act: 1.2957. Min Act: -0.0000

Data Index: 1459560 (Python Code)

Max Activating Token Index: 13

Text #18

Max Range: 1.6928. Min Range: -1.6928

Max Act: 1.1224. Min Act: -0.0001

Data Index: 1592864 (Python Code)

Max Activating Token Index: 106

Text #19

Max Range: 1.6928. Min Range: -1.6928

Max Act: 1.2278. Min Act: -0.0001

Data Index: 1637303 (Python Code)

Max Activating Token Index: 88