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

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

Neuron 983 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.9277. Min Range: -2.9277

Max Act: 2.9277. Min Act: -0.0000

Data Index: 1363234 (Python Code)

Max Activating Token Index: 880

Text #1

Max Range: 2.9277. Min Range: -2.9277

Max Act: 2.6402. Min Act: -0.0000

Data Index: 1457167 (Python Code)

Max Activating Token Index: 870

Text #2

Max Range: 2.9277. Min Range: -2.9277

Max Act: 2.6391. Min Act: -0.0000

Data Index: 1498960 (Python Code)

Max Activating Token Index: 502

Text #3

Max Range: 2.9277. Min Range: -2.9277

Max Act: 2.4617. Min Act: -0.0000

Data Index: 1532853 (Python Code)

Max Activating Token Index: 984

Text #4

Max Range: 2.9277. Min Range: -2.9277

Max Act: 2.2149. Min Act: -0.0000

Data Index: 1471539 (Python Code)

Max Activating Token Index: 103

Text #5

Max Range: 2.9277. Min Range: -2.9277

Max Act: 2.4613. Min Act: -0.0000

Data Index: 1548089 (Python Code)

Max Activating Token Index: 763

Text #6

Max Range: 2.9277. Min Range: -2.9277

Max Act: 2.3029. Min Act: -0.0000

Data Index: 1566435 (Python Code)

Max Activating Token Index: 53

Text #7

Max Range: 2.9277. Min Range: -2.9277

Max Act: 2.5479. Min Act: -0.0000

Data Index: 1422951 (Python Code)

Max Activating Token Index: 656

Text #8

Max Range: 2.9277. Min Range: -2.9277

Max Act: 2.3646. Min Act: -0.0000

Data Index: 1606093 (Python Code)

Max Activating Token Index: 1022

Text #9

Max Range: 2.9277. Min Range: -2.9277

Max Act: 2.3345. Min Act: -0.0000

Data Index: 1399962 (Python Code)

Max Activating Token Index: 132

Text #10

Max Range: 2.9277. Min Range: -2.9277

Max Act: 2.2052. Min Act: -0.0000

Data Index: 1623307 (Python Code)

Max Activating Token Index: 986

Text #11

Max Range: 2.9277. Min Range: -2.9277

Max Act: 2.3093. Min Act: -0.0000

Data Index: 1420750 (Python Code)

Max Activating Token Index: 531

Text #12

Max Range: 2.9277. Min Range: -2.9277

Max Act: 2.3213. Min Act: -0.0000

Data Index: 1648939 (Python Code)

Max Activating Token Index: 666

Text #13

Max Range: 2.9277. Min Range: -2.9277

Max Act: 2.1462. Min Act: -0.0000

Data Index: 1366869 (Python Code)

Max Activating Token Index: 256

Text #14

Max Range: 2.9277. Min Range: -2.9277

Max Act: 2.2526. Min Act: -0.0000

Data Index: 1633938 (Python Code)

Max Activating Token Index: 333

Text #15

Max Range: 2.9277. Min Range: -2.9277

Max Act: 2.2403. Min Act: -0.0000

Data Index: 1651279 (Python Code)

Max Activating Token Index: 952

Text #16

Max Range: 2.9277. Min Range: -2.9277

Max Act: 2.2496. Min Act: -0.0000

Data Index: 1428782 (Python Code)

Max Activating Token Index: 837

Text #17

Max Range: 2.9277. Min Range: -2.9277

Max Act: 2.2223. Min Act: -0.0000

Data Index: 1580938 (Python Code)

Max Activating Token Index: 132

Text #18

Max Range: 2.9277. Min Range: -2.9277

Max Act: 2.2328. Min Act: -0.0000

Data Index: 1600918 (Python Code)

Max Activating Token Index: 134

Text #19

Max Range: 2.9277. Min Range: -2.9277

Max Act: 2.3630. Min Act: -0.0000

Data Index: 1361595 (Python Code)

Max Activating Token Index: 637