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

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

Neuron 4013 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.9933. Min Range: -2.9933

Max Act: 2.9933. Min Act: -0.0000

Data Index: 1566064 (Python Code)

Max Activating Token Index: 774

Text #1

Max Range: 2.9933. Min Range: -2.9933

Max Act: 2.6002. Min Act: -0.0000

Data Index: 1438202 (Python Code)

Max Activating Token Index: 860

Text #2

Max Range: 2.9933. Min Range: -2.9933

Max Act: 2.2352. Min Act: -0.0000

Data Index: 1510299 (Python Code)

Max Activating Token Index: 754

Text #3

Max Range: 2.9933. Min Range: -2.9933

Max Act: 2.7738. Min Act: -0.0000

Data Index: 1387818 (Python Code)

Max Activating Token Index: 720

Text #4

Max Range: 2.9933. Min Range: -2.9933

Max Act: 2.4194. Min Act: -0.0000

Data Index: 1510489 (Python Code)

Max Activating Token Index: 651

Text #5

Max Range: 2.9933. Min Range: -2.9933

Max Act: 2.1715. Min Act: -0.0000

Data Index: 1383952 (Python Code)

Max Activating Token Index: 626

Text #6

Max Range: 2.9933. Min Range: -2.9933

Max Act: 2.7111. Min Act: -0.0000

Data Index: 1488854 (Python Code)

Max Activating Token Index: 927

Text #7

Max Range: 2.9933. Min Range: -2.9933

Max Act: 2.4951. Min Act: -0.0000

Data Index: 1503934 (Python Code)

Max Activating Token Index: 932

Text #8

Max Range: 2.9933. Min Range: -2.9933

Max Act: 2.3542. Min Act: -0.0000

Data Index: 1510770 (Python Code)

Max Activating Token Index: 922

Text #9

Max Range: 2.9933. Min Range: -2.9933

Max Act: 2.4625. Min Act: -0.0000

Data Index: 1479279 (Python Code)

Max Activating Token Index: 866

Text #10

Max Range: 2.9933. Min Range: -2.9933

Max Act: 2.4442. Min Act: -0.0000

Data Index: 1400971 (Python Code)

Max Activating Token Index: 966

Text #11

Max Range: 2.9933. Min Range: -2.9933

Max Act: 2.1967. Min Act: -0.0000

Data Index: 1397726 (Python Code)

Max Activating Token Index: 855

Text #12

Max Range: 2.9933. Min Range: -2.9933

Max Act: 1.7638. Min Act: -0.0000

Data Index: 1376281 (Python Code)

Max Activating Token Index: 819

Text #13

Max Range: 2.9933. Min Range: -2.9933

Max Act: 2.1473. Min Act: -0.0000

Data Index: 1435662 (Python Code)

Max Activating Token Index: 838

Text #14

Max Range: 2.9933. Min Range: -2.9933

Max Act: 2.1517. Min Act: -0.0000

Data Index: 1449118 (Python Code)

Max Activating Token Index: 618

Text #15

Max Range: 2.9933. Min Range: -2.9933

Max Act: 2.4857. Min Act: -0.0000

Data Index: 1554486 (Python Code)

Max Activating Token Index: 931

Text #16

Max Range: 2.9933. Min Range: -2.9933

Max Act: 2.0330. Min Act: -0.0000

Data Index: 1642928 (Python Code)

Max Activating Token Index: 899

Text #17

Max Range: 2.9933. Min Range: -2.9933

Max Act: 2.2417. Min Act: -0.0000

Data Index: 1589189 (Python Code)

Max Activating Token Index: 706

Text #18

Max Range: 2.9933. Min Range: -2.9933

Max Act: 2.0874. Min Act: -0.0000

Data Index: 1528504 (Python Code)

Max Activating Token Index: 968

Text #19

Max Range: 2.9933. Min Range: -2.9933

Max Act: 2.2104. Min Act: -0.0000

Data Index: 1597956 (Python Code)

Max Activating Token Index: 796