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

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

Neuron 5474 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0646. Min Range: -0.0646

Max Act: 0.0646. Min Act: -0.0002

Data Index: 458514 (C4 (Web Text))

Max Activating Token Index: 417

Text #1

Max Range: 0.0646. Min Range: -0.0646

Max Act: 0.0377. Min Act: -0.0002

Data Index: 1245435 (C4 (Web Text))

Max Activating Token Index: 282

Text #2

Max Range: 0.0646. Min Range: -0.0646

Max Act: 0.0430. Min Act: -0.0002

Data Index: 718928 (C4 (Web Text))

Max Activating Token Index: 694

Text #3

Max Range: 0.0646. Min Range: -0.0646

Max Act: 0.0488. Min Act: -0.0002

Data Index: 48360 (C4 (Web Text))

Max Activating Token Index: 380

Text #4

Max Range: 0.0646. Min Range: -0.0646

Max Act: 0.0561. Min Act: -0.0002

Data Index: 1085295 (C4 (Web Text))

Max Activating Token Index: 876

Text #5

Max Range: 0.0646. Min Range: -0.0646

Max Act: 0.0342. Min Act: -0.0002

Data Index: 150873 (C4 (Web Text))

Max Activating Token Index: 299

Text #6

Max Range: 0.0646. Min Range: -0.0646

Max Act: 0.0507. Min Act: -0.0002

Data Index: 944444 (C4 (Web Text))

Max Activating Token Index: 771

Text #7

Max Range: 0.0646. Min Range: -0.0646

Max Act: 0.0538. Min Act: -0.0002

Data Index: 849393 (C4 (Web Text))

Max Activating Token Index: 500

Text #8

Max Range: 0.0646. Min Range: -0.0646

Max Act: 0.0557. Min Act: -0.0002

Data Index: 1174922 (C4 (Web Text))

Max Activating Token Index: 96

Text #9

Max Range: 0.0646. Min Range: -0.0646

Max Act: 0.0454. Min Act: -0.0002

Data Index: 457254 (C4 (Web Text))

Max Activating Token Index: 314

Text #10

Max Range: 0.0646. Min Range: -0.0646

Max Act: 0.0533. Min Act: -0.0002

Data Index: 840957 (C4 (Web Text))

Max Activating Token Index: 71

Text #11

Max Range: 0.0646. Min Range: -0.0646

Max Act: 0.0524. Min Act: -0.0002

Data Index: 456104 (C4 (Web Text))

Max Activating Token Index: 204

Text #12

Max Range: 0.0646. Min Range: -0.0646

Max Act: 0.0468. Min Act: -0.0002

Data Index: 657431 (C4 (Web Text))

Max Activating Token Index: 792

Text #13

Max Range: 0.0646. Min Range: -0.0646

Max Act: 0.0361. Min Act: -0.0002

Data Index: 940073 (C4 (Web Text))

Max Activating Token Index: 717

Text #14

Max Range: 0.0646. Min Range: -0.0646

Max Act: 0.0522. Min Act: -0.0002

Data Index: 1465113 (Python Code)

Max Activating Token Index: 928

Text #15

Max Range: 0.0646. Min Range: -0.0646

Max Act: 0.0558. Min Act: -0.0002

Data Index: 977381 (C4 (Web Text))

Max Activating Token Index: 663

Text #16

Max Range: 0.0646. Min Range: -0.0646

Max Act: 0.0621. Min Act: -0.0002

Data Index: 1150041 (C4 (Web Text))

Max Activating Token Index: 456

Text #17

Max Range: 0.0646. Min Range: -0.0646

Max Act: 0.0445. Min Act: -0.0002

Data Index: 753767 (C4 (Web Text))

Max Activating Token Index: 740

Text #18

Max Range: 0.0646. Min Range: -0.0646

Max Act: 0.0544. Min Act: -0.0002

Data Index: 806913 (C4 (Web Text))

Max Activating Token Index: 734

Text #19

Max Range: 0.0646. Min Range: -0.0646

Max Act: 0.0428. Min Act: -0.0002

Data Index: 561280 (C4 (Web Text))

Max Activating Token Index: 728