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

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

Neuron 4882 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: 0.0578. Min Range: -0.0578

Max Act: 0.0578. Min Act: -0.0002

Data Index: 1419973 (Python Code)

Max Activating Token Index: 622

Text #1

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0555. Min Act: -0.0002

Data Index: 59920 (C4 (Web Text))

Max Activating Token Index: 628

Text #2

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0534. Min Act: -0.0002

Data Index: 1500129 (Python Code)

Max Activating Token Index: 122

Text #3

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0533. Min Act: -0.0002

Data Index: 1428043 (Python Code)

Max Activating Token Index: 229

Text #4

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0522. Min Act: -0.0002

Data Index: 996360 (C4 (Web Text))

Max Activating Token Index: 298

Text #5

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0520. Min Act: -0.0002

Data Index: 564754 (C4 (Web Text))

Max Activating Token Index: 535

Text #6

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0507. Min Act: -0.0002

Data Index: 1553262 (Python Code)

Max Activating Token Index: 812

Text #7

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0509. Min Act: -0.0002

Data Index: 39586 (C4 (Web Text))

Max Activating Token Index: 424

Text #8

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0473. Min Act: -0.0002

Data Index: 1092593 (C4 (Web Text))

Max Activating Token Index: 556

Text #9

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0460. Min Act: -0.0002

Data Index: 191394 (C4 (Web Text))

Max Activating Token Index: 439

Text #10

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0440. Min Act: -0.0002

Data Index: 869262 (C4 (Web Text))

Max Activating Token Index: 646

Text #11

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0469. Min Act: -0.0002

Data Index: 1502473 (Python Code)

Max Activating Token Index: 922

Text #12

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0458. Min Act: -0.0002

Data Index: 1550455 (Python Code)

Max Activating Token Index: 769

Text #13

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0422. Min Act: -0.0002

Data Index: 661287 (C4 (Web Text))

Max Activating Token Index: 141

Text #14

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0451. Min Act: -0.0002

Data Index: 64748 (C4 (Web Text))

Max Activating Token Index: 945

Text #15

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0415. Min Act: -0.0002

Data Index: 465765 (C4 (Web Text))

Max Activating Token Index: 298

Text #16

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0410. Min Act: -0.0002

Data Index: 97536 (C4 (Web Text))

Max Activating Token Index: 329

Text #17

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0410. Min Act: -0.0002

Data Index: 1585636 (Python Code)

Max Activating Token Index: 424

Text #18

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0407. Min Act: -0.0002

Data Index: 1636909 (Python Code)

Max Activating Token Index: 591

Text #19

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0404. Min Act: -0.0002

Data Index: 746415 (C4 (Web Text))

Max Activating Token Index: 195