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

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

Neuron 3795 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: 0.4086. Min Range: -0.4086

Max Act: 0.4086. Min Act: -0.0000

Data Index: 1432912 (Python Code)

Max Activating Token Index: 971

Text #1

Max Range: 0.4086. Min Range: -0.4086

Max Act: 0.3549. Min Act: 0.0000

Data Index: 1583030 (Python Code)

Max Activating Token Index: 125

Text #2

Max Range: 0.4086. Min Range: -0.4086

Max Act: 0.3383. Min Act: -0.0000

Data Index: 1403258 (Python Code)

Max Activating Token Index: 690

Text #3

Max Range: 0.4086. Min Range: -0.4086

Max Act: 0.3337. Min Act: 0.0000

Data Index: 1428299 (Python Code)

Max Activating Token Index: 344

Text #4

Max Range: 0.4086. Min Range: -0.4086

Max Act: 0.3205. Min Act: -0.0000

Data Index: 1587377 (Python Code)

Max Activating Token Index: 259

Text #5

Max Range: 0.4086. Min Range: -0.4086

Max Act: 0.2937. Min Act: 0.0000

Data Index: 1568724 (Python Code)

Max Activating Token Index: 874

Text #6

Max Range: 0.4086. Min Range: -0.4086

Max Act: 0.2800. Min Act: 0.0000

Data Index: 1364077 (Python Code)

Max Activating Token Index: 775

Text #7

Max Range: 0.4086. Min Range: -0.4086

Max Act: 0.2855. Min Act: 0.0001

Data Index: 1652096 (Python Code)

Max Activating Token Index: 691

Text #8

Max Range: 0.4086. Min Range: -0.4086

Max Act: 0.2613. Min Act: -0.0000

Data Index: 1559537 (Python Code)

Max Activating Token Index: 212

Text #9

Max Range: 0.4086. Min Range: -0.4086

Max Act: 0.2637. Min Act: 0.0001

Data Index: 1360654 (Python Code)

Max Activating Token Index: 628

Text #10

Max Range: 0.4086. Min Range: -0.4086

Max Act: 0.2502. Min Act: 0.0001

Data Index: 1376113 (Python Code)

Max Activating Token Index: 983

Text #11

Max Range: 0.4086. Min Range: -0.4086

Max Act: 0.2627. Min Act: -0.0000

Data Index: 1458440 (Python Code)

Max Activating Token Index: 659

Text #12

Max Range: 0.4086. Min Range: -0.4086

Max Act: 0.2521. Min Act: 0.0000

Data Index: 1376040 (Python Code)

Max Activating Token Index: 542

Text #13

Max Range: 0.4086. Min Range: -0.4086

Max Act: 0.2598. Min Act: 0.0001

Data Index: 1551680 (Python Code)

Max Activating Token Index: 94

Text #14

Max Range: 0.4086. Min Range: -0.4086

Max Act: 0.2417. Min Act: 0.0002

Data Index: 1522269 (Python Code)

Max Activating Token Index: 305

Text #15

Max Range: 0.4086. Min Range: -0.4086

Max Act: 0.2492. Min Act: -0.0000

Data Index: 1384032 (Python Code)

Max Activating Token Index: 672

Text #16

Max Range: 0.4086. Min Range: -0.4086

Max Act: 0.2572. Min Act: 0.0002

Data Index: 1413637 (Python Code)

Max Activating Token Index: 93

Text #17

Max Range: 0.4086. Min Range: -0.4086

Max Act: 0.2534. Min Act: 0.0000

Data Index: 1421784 (Python Code)

Max Activating Token Index: 394

Text #18

Max Range: 0.4086. Min Range: -0.4086

Max Act: 0.2422. Min Act: 0.0001

Data Index: 1653050 (Python Code)

Max Activating Token Index: 528

Text #19

Max Range: 0.4086. Min Range: -0.4086

Max Act: 0.2475. Min Act: 0.0001

Data Index: 1582653 (Python Code)

Max Activating Token Index: 711