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

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

Neuron 5616 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.5061. Min Range: -6.5061

Max Act: 6.5061. Min Act: -0.0000

Data Index: 1653823 (Python Code)

Max Activating Token Index: 439

Text #1

Max Range: 6.5061. Min Range: -6.5061

Max Act: 5.1355. Min Act: -0.0000

Data Index: 1379371 (Python Code)

Max Activating Token Index: 966

Text #2

Max Range: 6.5061. Min Range: -6.5061

Max Act: 4.8916. Min Act: -0.0000

Data Index: 1593830 (Python Code)

Max Activating Token Index: 282

Text #3

Max Range: 6.5061. Min Range: -6.5061

Max Act: 3.9268. Min Act: -0.0000

Data Index: 1591314 (Python Code)

Max Activating Token Index: 163

Text #4

Max Range: 6.5061. Min Range: -6.5061

Max Act: 3.9030. Min Act: -0.0000

Data Index: 1591241 (Python Code)

Max Activating Token Index: 625

Text #5

Max Range: 6.5061. Min Range: -6.5061

Max Act: 3.5499. Min Act: -0.0000

Data Index: 1529547 (Python Code)

Max Activating Token Index: 963

Text #6

Max Range: 6.5061. Min Range: -6.5061

Max Act: 3.8207. Min Act: -0.0000

Data Index: 690247 (C4 (Web Text))

Max Activating Token Index: 286

Text #7

Max Range: 6.5061. Min Range: -6.5061

Max Act: 3.7837. Min Act: -0.0000

Data Index: 1551629 (Python Code)

Max Activating Token Index: 109

Text #8

Max Range: 6.5061. Min Range: -6.5061

Max Act: 3.1155. Min Act: -0.0000

Data Index: 1545632 (Python Code)

Max Activating Token Index: 239

Text #9

Max Range: 6.5061. Min Range: -6.5061

Max Act: 3.7049. Min Act: -0.0000

Data Index: 1567866 (Python Code)

Max Activating Token Index: 937

Text #10

Max Range: 6.5061. Min Range: -6.5061

Max Act: 3.5467. Min Act: -0.0000

Data Index: 1606748 (Python Code)

Max Activating Token Index: 206

Text #11

Max Range: 6.5061. Min Range: -6.5061

Max Act: 3.5680. Min Act: -0.0000

Data Index: 1539732 (Python Code)

Max Activating Token Index: 562

Text #12

Max Range: 6.5061. Min Range: -6.5061

Max Act: 3.3777. Min Act: -0.0000

Data Index: 1513971 (Python Code)

Max Activating Token Index: 775

Text #13

Max Range: 6.5061. Min Range: -6.5061

Max Act: 3.2603. Min Act: -0.0000

Data Index: 1404360 (Python Code)

Max Activating Token Index: 744

Text #14

Max Range: 6.5061. Min Range: -6.5061

Max Act: 3.0408. Min Act: -0.0000

Data Index: 1606674 (Python Code)

Max Activating Token Index: 1005

Text #15

Max Range: 6.5061. Min Range: -6.5061

Max Act: 3.1164. Min Act: -0.0000

Data Index: 1534971 (Python Code)

Max Activating Token Index: 407

Text #16

Max Range: 6.5061. Min Range: -6.5061

Max Act: 3.2719. Min Act: -0.0000

Data Index: 1610671 (Python Code)

Max Activating Token Index: 88

Text #17

Max Range: 6.5061. Min Range: -6.5061

Max Act: 3.2579. Min Act: -0.0000

Data Index: 1474918 (Python Code)

Max Activating Token Index: 317

Text #18

Max Range: 6.5061. Min Range: -6.5061

Max Act: 3.0762. Min Act: -0.0000

Data Index: 1422938 (Python Code)

Max Activating Token Index: 504

Text #19

Max Range: 6.5061. Min Range: -6.5061

Max Act: 3.0748. Min Act: -0.0000

Data Index: 1494289 (Python Code)

Max Activating Token Index: 838