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

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

Neuron 2310 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2900. Min Range: -1.2900

Max Act: 1.2900. Min Act: -0.0000

Data Index: 1420964 (Python Code)

Max Activating Token Index: 824

Text #1

Max Range: 1.2900. Min Range: -1.2900

Max Act: 1.2511. Min Act: -0.0000

Data Index: 1609352 (Python Code)

Max Activating Token Index: 1007

Text #2

Max Range: 1.2900. Min Range: -1.2900

Max Act: 1.2726. Min Act: -0.0000

Data Index: 1645772 (Python Code)

Max Activating Token Index: 275

Text #3

Max Range: 1.2900. Min Range: -1.2900

Max Act: 1.1894. Min Act: -0.0000

Data Index: 1440703 (Python Code)

Max Activating Token Index: 104

Text #4

Max Range: 1.2900. Min Range: -1.2900

Max Act: 1.2699. Min Act: -0.0000

Data Index: 1367099 (Python Code)

Max Activating Token Index: 78

Text #5

Max Range: 1.2900. Min Range: -1.2900

Max Act: 1.1293. Min Act: -0.0000

Data Index: 1558636 (Python Code)

Max Activating Token Index: 558

Text #6

Max Range: 1.2900. Min Range: -1.2900

Max Act: 1.1489. Min Act: -0.0000

Data Index: 1364815 (Python Code)

Max Activating Token Index: 971

Text #7

Max Range: 1.2900. Min Range: -1.2900

Max Act: 1.0938. Min Act: -0.0000

Data Index: 50444 (C4 (Web Text))

Max Activating Token Index: 788

Text #8

Max Range: 1.2900. Min Range: -1.2900

Max Act: 1.0451. Min Act: -0.0000

Data Index: 1463735 (Python Code)

Max Activating Token Index: 947

Text #9

Max Range: 1.2900. Min Range: -1.2900

Max Act: 1.1415. Min Act: -0.0000

Data Index: 1605621 (Python Code)

Max Activating Token Index: 251

Text #10

Max Range: 1.2900. Min Range: -1.2900

Max Act: 1.1120. Min Act: -0.0000

Data Index: 1644120 (Python Code)

Max Activating Token Index: 633

Text #11

Max Range: 1.2900. Min Range: -1.2900

Max Act: 1.0930. Min Act: -0.0000

Data Index: 1377964 (Python Code)

Max Activating Token Index: 351

Text #12

Max Range: 1.2900. Min Range: -1.2900

Max Act: 1.0568. Min Act: -0.0000

Data Index: 1569297 (Python Code)

Max Activating Token Index: 524

Text #13

Max Range: 1.2900. Min Range: -1.2900

Max Act: 1.0479. Min Act: -0.0000

Data Index: 1360445 (Python Code)

Max Activating Token Index: 576

Text #14

Max Range: 1.2900. Min Range: -1.2900

Max Act: 0.9800. Min Act: -0.0000

Data Index: 1364180 (Python Code)

Max Activating Token Index: 366

Text #15

Max Range: 1.2900. Min Range: -1.2900

Max Act: 1.0510. Min Act: -0.0000

Data Index: 1540966 (Python Code)

Max Activating Token Index: 68

Text #16

Max Range: 1.2900. Min Range: -1.2900

Max Act: 1.0387. Min Act: -0.0000

Data Index: 1653571 (Python Code)

Max Activating Token Index: 1015

Text #17

Max Range: 1.2900. Min Range: -1.2900

Max Act: 1.0600. Min Act: -0.0000

Data Index: 973448 (C4 (Web Text))

Max Activating Token Index: 893

Text #18

Max Range: 1.2900. Min Range: -1.2900

Max Act: 0.9899. Min Act: -0.0000

Data Index: 1625734 (Python Code)

Max Activating Token Index: 396

Text #19

Max Range: 1.2900. Min Range: -1.2900

Max Act: 0.9903. Min Act: -0.0000

Data Index: 1373924 (Python Code)

Max Activating Token Index: 464