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

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

Neuron 2607 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3037. Min Range: -0.3037

Max Act: 0.3037. Min Act: -0.0000

Data Index: 1510245 (Python Code)

Max Activating Token Index: 583

Text #1

Max Range: 0.3037. Min Range: -0.3037

Max Act: 0.2506. Min Act: -0.0000

Data Index: 1538036 (Python Code)

Max Activating Token Index: 589

Text #2

Max Range: 0.3037. Min Range: -0.3037

Max Act: 0.2314. Min Act: -0.0000

Data Index: 1368295 (Python Code)

Max Activating Token Index: 905

Text #3

Max Range: 0.3037. Min Range: -0.3037

Max Act: 0.2444. Min Act: -0.0000

Data Index: 1441596 (Python Code)

Max Activating Token Index: 723

Text #4

Max Range: 0.3037. Min Range: -0.3037

Max Act: 0.2289. Min Act: -0.0000

Data Index: 1425649 (Python Code)

Max Activating Token Index: 1013

Text #5

Max Range: 0.3037. Min Range: -0.3037

Max Act: 0.2274. Min Act: -0.0000

Data Index: 1652874 (Python Code)

Max Activating Token Index: 155

Text #6

Max Range: 0.3037. Min Range: -0.3037

Max Act: 0.2149. Min Act: -0.0000

Data Index: 1490312 (Python Code)

Max Activating Token Index: 161

Text #7

Max Range: 0.3037. Min Range: -0.3037

Max Act: 0.2090. Min Act: -0.0000

Data Index: 1559226 (Python Code)

Max Activating Token Index: 499

Text #8

Max Range: 0.3037. Min Range: -0.3037

Max Act: 0.2069. Min Act: -0.0000

Data Index: 1538980 (Python Code)

Max Activating Token Index: 257

Text #9

Max Range: 0.3037. Min Range: -0.3037

Max Act: 0.1970. Min Act: -0.0000

Data Index: 1505655 (Python Code)

Max Activating Token Index: 70

Text #10

Max Range: 0.3037. Min Range: -0.3037

Max Act: 0.1953. Min Act: -0.0000

Data Index: 1637055 (Python Code)

Max Activating Token Index: 167

Text #11

Max Range: 0.3037. Min Range: -0.3037

Max Act: 0.1886. Min Act: -0.0000

Data Index: 1590129 (Python Code)

Max Activating Token Index: 41

Text #12

Max Range: 0.3037. Min Range: -0.3037

Max Act: 0.1951. Min Act: -0.0000

Data Index: 1584359 (Python Code)

Max Activating Token Index: 304

Text #13

Max Range: 0.3037. Min Range: -0.3037

Max Act: 0.1915. Min Act: -0.0000

Data Index: 1592551 (Python Code)

Max Activating Token Index: 633

Text #14

Max Range: 0.3037. Min Range: -0.3037

Max Act: 0.1861. Min Act: -0.0000

Data Index: 1449697 (Python Code)

Max Activating Token Index: 98

Text #15

Max Range: 0.3037. Min Range: -0.3037

Max Act: 0.1898. Min Act: -0.0000

Data Index: 1490361 (Python Code)

Max Activating Token Index: 933

Text #16

Max Range: 0.3037. Min Range: -0.3037

Max Act: 0.1793. Min Act: -0.0000

Data Index: 1582947 (Python Code)

Max Activating Token Index: 466

Text #17

Max Range: 0.3037. Min Range: -0.3037

Max Act: 0.1806. Min Act: -0.0000

Data Index: 1531654 (Python Code)

Max Activating Token Index: 300

Text #18

Max Range: 0.3037. Min Range: -0.3037

Max Act: 0.1867. Min Act: -0.0000

Data Index: 1379196 (Python Code)

Max Activating Token Index: 365

Text #19

Max Range: 0.3037. Min Range: -0.3037

Max Act: 0.1857. Min Act: -0.0000

Data Index: 1222985 (C4 (Web Text))

Max Activating Token Index: 905