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

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

Neuron 3649 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2969. Min Range: -2.2969

Max Act: 2.2969. Min Act: -0.0000

Data Index: 1497240 (Python Code)

Max Activating Token Index: 399

Text #1

Max Range: 2.2969. Min Range: -2.2969

Max Act: 2.0191. Min Act: -0.0001

Data Index: 1452483 (Python Code)

Max Activating Token Index: 208

Text #2

Max Range: 2.2969. Min Range: -2.2969

Max Act: 2.0364. Min Act: -0.0000

Data Index: 1443268 (Python Code)

Max Activating Token Index: 160

Text #3

Max Range: 2.2969. Min Range: -2.2969

Max Act: 1.8064. Min Act: -0.0001

Data Index: 1535748 (Python Code)

Max Activating Token Index: 425

Text #4

Max Range: 2.2969. Min Range: -2.2969

Max Act: 1.9007. Min Act: -0.0000

Data Index: 1446325 (Python Code)

Max Activating Token Index: 624

Text #5

Max Range: 2.2969. Min Range: -2.2969

Max Act: 1.7626. Min Act: -0.0000

Data Index: 1650932 (Python Code)

Max Activating Token Index: 75

Text #6

Max Range: 2.2969. Min Range: -2.2969

Max Act: 1.7521. Min Act: -0.0001

Data Index: 1620200 (Python Code)

Max Activating Token Index: 537

Text #7

Max Range: 2.2969. Min Range: -2.2969

Max Act: 1.8576. Min Act: -0.0000

Data Index: 1437818 (Python Code)

Max Activating Token Index: 646

Text #8

Max Range: 2.2969. Min Range: -2.2969

Max Act: 1.7487. Min Act: -0.0000

Data Index: 1394478 (Python Code)

Max Activating Token Index: 652

Text #9

Max Range: 2.2969. Min Range: -2.2969

Max Act: 1.9222. Min Act: -0.0001

Data Index: 1560968 (Python Code)

Max Activating Token Index: 705

Text #10

Max Range: 2.2969. Min Range: -2.2969

Max Act: 1.7992. Min Act: -0.0000

Data Index: 1509049 (Python Code)

Max Activating Token Index: 150

Text #11

Max Range: 2.2969. Min Range: -2.2969

Max Act: 1.9009. Min Act: -0.0001

Data Index: 1382998 (Python Code)

Max Activating Token Index: 385

Text #12

Max Range: 2.2969. Min Range: -2.2969

Max Act: 1.6962. Min Act: -0.0000

Data Index: 1481779 (Python Code)

Max Activating Token Index: 564

Text #13

Max Range: 2.2969. Min Range: -2.2969

Max Act: 1.6760. Min Act: -0.0000

Data Index: 1529143 (Python Code)

Max Activating Token Index: 641

Text #14

Max Range: 2.2969. Min Range: -2.2969

Max Act: 1.6633. Min Act: -0.0000

Data Index: 1478142 (Python Code)

Max Activating Token Index: 684

Text #15

Max Range: 2.2969. Min Range: -2.2969

Max Act: 1.8457. Min Act: -0.0001

Data Index: 1497724 (Python Code)

Max Activating Token Index: 821

Text #16

Max Range: 2.2969. Min Range: -2.2969

Max Act: 1.7463. Min Act: -0.0000

Data Index: 1636534 (Python Code)

Max Activating Token Index: 555

Text #17

Max Range: 2.2969. Min Range: -2.2969

Max Act: 1.5187. Min Act: -0.0000

Data Index: 1399349 (Python Code)

Max Activating Token Index: 347

Text #18

Max Range: 2.2969. Min Range: -2.2969

Max Act: 2.0634. Min Act: -0.0000

Data Index: 1498922 (Python Code)

Max Activating Token Index: 437

Text #19

Max Range: 2.2969. Min Range: -2.2969

Max Act: 1.6468. Min Act: -0.0000

Data Index: 1461028 (Python Code)

Max Activating Token Index: 954