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

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

Neuron 2054 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3514. Min Range: -1.3514

Max Act: 1.3514. Min Act: -0.0000

Data Index: 1383929 (Python Code)

Max Activating Token Index: 302

Text #1

Max Range: 1.3514. Min Range: -1.3514

Max Act: 1.2623. Min Act: -0.0000

Data Index: 1449365 (Python Code)

Max Activating Token Index: 40

Text #2

Max Range: 1.3514. Min Range: -1.3514

Max Act: 1.2579. Min Act: -0.0000

Data Index: 1504985 (Python Code)

Max Activating Token Index: 545

Text #3

Max Range: 1.3514. Min Range: -1.3514

Max Act: 1.1757. Min Act: -0.0000

Data Index: 1620130 (Python Code)

Max Activating Token Index: 203

Text #4

Max Range: 1.3514. Min Range: -1.3514

Max Act: 1.1225. Min Act: -0.0000

Data Index: 1586417 (Python Code)

Max Activating Token Index: 238

Text #5

Max Range: 1.3514. Min Range: -1.3514

Max Act: 1.1139. Min Act: -0.0000

Data Index: 1429968 (Python Code)

Max Activating Token Index: 965

Text #6

Max Range: 1.3514. Min Range: -1.3514

Max Act: 1.1157. Min Act: -0.0000

Data Index: 1566408 (Python Code)

Max Activating Token Index: 906

Text #7

Max Range: 1.3514. Min Range: -1.3514

Max Act: 1.0951. Min Act: -0.0000

Data Index: 1626449 (Python Code)

Max Activating Token Index: 716

Text #8

Max Range: 1.3514. Min Range: -1.3514

Max Act: 1.0428. Min Act: -0.0000

Data Index: 1645076 (Python Code)

Max Activating Token Index: 398

Text #9

Max Range: 1.3514. Min Range: -1.3514

Max Act: 0.9543. Min Act: -0.0000

Data Index: 1496544 (Python Code)

Max Activating Token Index: 387

Text #10

Max Range: 1.3514. Min Range: -1.3514

Max Act: 1.0369. Min Act: -0.0000

Data Index: 1583487 (Python Code)

Max Activating Token Index: 402

Text #11

Max Range: 1.3514. Min Range: -1.3514

Max Act: 0.9576. Min Act: 0.0000

Data Index: 1473776 (Python Code)

Max Activating Token Index: 540

Text #12

Max Range: 1.3514. Min Range: -1.3514

Max Act: 0.9821. Min Act: -0.0000

Data Index: 1451523 (Python Code)

Max Activating Token Index: 21

Text #13

Max Range: 1.3514. Min Range: -1.3514

Max Act: 1.0056. Min Act: -0.0000

Data Index: 1650844 (Python Code)

Max Activating Token Index: 57

Text #14

Max Range: 1.3514. Min Range: -1.3514

Max Act: 0.8954. Min Act: -0.0000

Data Index: 1640768 (Python Code)

Max Activating Token Index: 705

Text #15

Max Range: 1.3514. Min Range: -1.3514

Max Act: 0.8961. Min Act: -0.0000

Data Index: 1465906 (Python Code)

Max Activating Token Index: 1005

Text #16

Max Range: 1.3514. Min Range: -1.3514

Max Act: 0.9149. Min Act: -0.0000

Data Index: 1595858 (Python Code)

Max Activating Token Index: 572

Text #17

Max Range: 1.3514. Min Range: -1.3514

Max Act: 0.8857. Min Act: -0.0000

Data Index: 1546007 (Python Code)

Max Activating Token Index: 97

Text #18

Max Range: 1.3514. Min Range: -1.3514

Max Act: 0.8785. Min Act: -0.0000

Data Index: 1532687 (Python Code)

Max Activating Token Index: 457

Text #19

Max Range: 1.3514. Min Range: -1.3514

Max Act: 0.8862. Min Act: -0.0000

Data Index: 1590194 (Python Code)

Max Activating Token Index: 483