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

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

Neuron 4628 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: 3.3940. Min Range: -3.3940

Max Act: 3.3940. Min Act: -0.0000

Data Index: 1613313 (Python Code)

Max Activating Token Index: 535

Text #1

Max Range: 3.3940. Min Range: -3.3940

Max Act: 3.1311. Min Act: -0.0000

Data Index: 1576671 (Python Code)

Max Activating Token Index: 633

Text #2

Max Range: 3.3940. Min Range: -3.3940

Max Act: 2.9901. Min Act: -0.0000

Data Index: 1648296 (Python Code)

Max Activating Token Index: 298

Text #3

Max Range: 3.3940. Min Range: -3.3940

Max Act: 3.2737. Min Act: -0.0000

Data Index: 1575747 (Python Code)

Max Activating Token Index: 133

Text #4

Max Range: 3.3940. Min Range: -3.3940

Max Act: 2.9529. Min Act: -0.0001

Data Index: 1366833 (Python Code)

Max Activating Token Index: 81

Text #5

Max Range: 3.3940. Min Range: -3.3940

Max Act: 3.1745. Min Act: -0.0000

Data Index: 1449329 (Python Code)

Max Activating Token Index: 13

Text #6

Max Range: 3.3940. Min Range: -3.3940

Max Act: 3.0266. Min Act: -0.0000

Data Index: 1624051 (Python Code)

Max Activating Token Index: 12

Text #7

Max Range: 3.3940. Min Range: -3.3940

Max Act: 3.1606. Min Act: -0.0000

Data Index: 1374190 (Python Code)

Max Activating Token Index: 11

Text #8

Max Range: 3.3940. Min Range: -3.3940

Max Act: 3.1606. Min Act: -0.0000

Data Index: 1510053 (Python Code)

Max Activating Token Index: 11

Text #9

Max Range: 3.3940. Min Range: -3.3940

Max Act: 3.2844. Min Act: -0.0000

Data Index: 1654424 (Python Code)

Max Activating Token Index: 374

Text #10

Max Range: 3.3940. Min Range: -3.3940

Max Act: 2.6338. Min Act: -0.0000

Data Index: 1635978 (Python Code)

Max Activating Token Index: 152

Text #11

Max Range: 3.3940. Min Range: -3.3940

Max Act: 3.0095. Min Act: -0.0000

Data Index: 1654149 (Python Code)

Max Activating Token Index: 96

Text #12

Max Range: 3.3940. Min Range: -3.3940

Max Act: 3.0018. Min Act: -0.0000

Data Index: 1464852 (Python Code)

Max Activating Token Index: 456

Text #13

Max Range: 3.3940. Min Range: -3.3940

Max Act: 3.0135. Min Act: -0.0000

Data Index: 1545220 (Python Code)

Max Activating Token Index: 105

Text #14

Max Range: 3.3940. Min Range: -3.3940

Max Act: 2.8621. Min Act: -0.0000

Data Index: 1531657 (Python Code)

Max Activating Token Index: 676

Text #15

Max Range: 3.3940. Min Range: -3.3940

Max Act: 2.9087. Min Act: -0.0000

Data Index: 1493007 (Python Code)

Max Activating Token Index: 816

Text #16

Max Range: 3.3940. Min Range: -3.3940

Max Act: 2.8266. Min Act: -0.0000

Data Index: 1538498 (Python Code)

Max Activating Token Index: 384

Text #17

Max Range: 3.3940. Min Range: -3.3940

Max Act: 2.9626. Min Act: -0.0000

Data Index: 1498091 (Python Code)

Max Activating Token Index: 272

Text #18

Max Range: 3.3940. Min Range: -3.3940

Max Act: 2.6638. Min Act: -0.0001

Data Index: 1390603 (Python Code)

Max Activating Token Index: 673

Text #19

Max Range: 3.3940. Min Range: -3.3940

Max Act: 2.4971. Min Act: -0.0000

Data Index: 1379839 (Python Code)

Max Activating Token Index: 962