Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1318 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 3.9531. Min Range: -3.9531

Max Act: 3.9531. Min Act: -0.0001

Data Index: 1444341 (Python Code)

Max Activating Token Index: 591

Text #1

Max Range: 3.9531. Min Range: -3.9531

Max Act: 3.5278. Min Act: -0.0001

Data Index: 1365318 (Python Code)

Max Activating Token Index: 485

Text #2

Max Range: 3.9531. Min Range: -3.9531

Max Act: 3.7570. Min Act: -0.0001

Data Index: 1622113 (Python Code)

Max Activating Token Index: 316

Text #3

Max Range: 3.9531. Min Range: -3.9531

Max Act: 3.6056. Min Act: -0.0001

Data Index: 1564760 (Python Code)

Max Activating Token Index: 387

Text #4

Max Range: 3.9531. Min Range: -3.9531

Max Act: 3.5530. Min Act: -0.0001

Data Index: 1576534 (Python Code)

Max Activating Token Index: 370

Text #5

Max Range: 3.9531. Min Range: -3.9531

Max Act: 3.1874. Min Act: -0.0001

Data Index: 1456212 (Python Code)

Max Activating Token Index: 818

Text #6

Max Range: 3.9531. Min Range: -3.9531

Max Act: 2.9307. Min Act: -0.0001

Data Index: 1463235 (Python Code)

Max Activating Token Index: 401

Text #7

Max Range: 3.9531. Min Range: -3.9531

Max Act: 2.7984. Min Act: -0.0001

Data Index: 1509784 (Python Code)

Max Activating Token Index: 843

Text #8

Max Range: 3.9531. Min Range: -3.9531

Max Act: 2.8872. Min Act: -0.0001

Data Index: 1547154 (Python Code)

Max Activating Token Index: 664

Text #9

Max Range: 3.9531. Min Range: -3.9531

Max Act: 2.8677. Min Act: -0.0001

Data Index: 1589506 (Python Code)

Max Activating Token Index: 933

Text #10

Max Range: 3.9531. Min Range: -3.9531

Max Act: 3.0025. Min Act: -0.0001

Data Index: 1548930 (Python Code)

Max Activating Token Index: 773

Text #11

Max Range: 3.9531. Min Range: -3.9531

Max Act: 2.4040. Min Act: -0.0001

Data Index: 1498386 (Python Code)

Max Activating Token Index: 843

Text #12

Max Range: 3.9531. Min Range: -3.9531

Max Act: 2.6641. Min Act: -0.0001

Data Index: 1634803 (Python Code)

Max Activating Token Index: 906

Text #13

Max Range: 3.9531. Min Range: -3.9531

Max Act: 2.7570. Min Act: -0.0001

Data Index: 1543033 (Python Code)

Max Activating Token Index: 801

Text #14

Max Range: 3.9531. Min Range: -3.9531

Max Act: 2.7292. Min Act: -0.0001

Data Index: 1536626 (Python Code)

Max Activating Token Index: 748

Text #15

Max Range: 3.9531. Min Range: -3.9531

Max Act: 2.9945. Min Act: -0.0001

Data Index: 1527761 (Python Code)

Max Activating Token Index: 481

Text #16

Max Range: 3.9531. Min Range: -3.9531

Max Act: 2.5816. Min Act: -0.0001

Data Index: 1465810 (Python Code)

Max Activating Token Index: 896

Text #17

Max Range: 3.9531. Min Range: -3.9531

Max Act: 2.5608. Min Act: -0.0001

Data Index: 1400952 (Python Code)

Max Activating Token Index: 159

Text #18

Max Range: 3.9531. Min Range: -3.9531

Max Act: 2.4279. Min Act: -0.0001

Data Index: 1567485 (Python Code)

Max Activating Token Index: 842

Text #19

Max Range: 3.9531. Min Range: -3.9531

Max Act: 2.4912. Min Act: -0.0001

Data Index: 1584183 (Python Code)

Max Activating Token Index: 338