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

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

Neuron 2859 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6864. Min Range: -1.6864

Max Act: 1.6864. Min Act: -0.0000

Data Index: 1504354 (Python Code)

Max Activating Token Index: 876

Text #1

Max Range: 1.6864. Min Range: -1.6864

Max Act: 1.4470. Min Act: -0.0000

Data Index: 1581924 (Python Code)

Max Activating Token Index: 1023

Text #2

Max Range: 1.6864. Min Range: -1.6864

Max Act: 1.4781. Min Act: -0.0000

Data Index: 1416233 (Python Code)

Max Activating Token Index: 43

Text #3

Max Range: 1.6864. Min Range: -1.6864

Max Act: 1.3991. Min Act: -0.0000

Data Index: 1650372 (Python Code)

Max Activating Token Index: 223

Text #4

Max Range: 1.6864. Min Range: -1.6864

Max Act: 1.4161. Min Act: -0.0000

Data Index: 1622950 (Python Code)

Max Activating Token Index: 346

Text #5

Max Range: 1.6864. Min Range: -1.6864

Max Act: 1.3308. Min Act: -0.0000

Data Index: 1543716 (Python Code)

Max Activating Token Index: 982

Text #6

Max Range: 1.6864. Min Range: -1.6864

Max Act: 1.3642. Min Act: -0.0000

Data Index: 1652355 (Python Code)

Max Activating Token Index: 119

Text #7

Max Range: 1.6864. Min Range: -1.6864

Max Act: 1.3171. Min Act: -0.0000

Data Index: 1439543 (Python Code)

Max Activating Token Index: 457

Text #8

Max Range: 1.6864. Min Range: -1.6864

Max Act: 1.2592. Min Act: -0.0000

Data Index: 1656720 (Python Code)

Max Activating Token Index: 333

Text #9

Max Range: 1.6864. Min Range: -1.6864

Max Act: 1.3646. Min Act: -0.0000

Data Index: 1401348 (Python Code)

Max Activating Token Index: 993

Text #10

Max Range: 1.6864. Min Range: -1.6864

Max Act: 1.3281. Min Act: -0.0000

Data Index: 1516731 (Python Code)

Max Activating Token Index: 448

Text #11

Max Range: 1.6864. Min Range: -1.6864

Max Act: 1.3460. Min Act: -0.0000

Data Index: 1482196 (Python Code)

Max Activating Token Index: 581

Text #12

Max Range: 1.6864. Min Range: -1.6864

Max Act: 1.3089. Min Act: -0.0000

Data Index: 1501413 (Python Code)

Max Activating Token Index: 11

Text #13

Max Range: 1.6864. Min Range: -1.6864

Max Act: 1.2920. Min Act: -0.0000

Data Index: 1361042 (Python Code)

Max Activating Token Index: 97

Text #14

Max Range: 1.6864. Min Range: -1.6864

Max Act: 1.3515. Min Act: -0.0000

Data Index: 1526342 (Python Code)

Max Activating Token Index: 700

Text #15

Max Range: 1.6864. Min Range: -1.6864

Max Act: 1.2440. Min Act: -0.0000

Data Index: 1479621 (Python Code)

Max Activating Token Index: 474

Text #16

Max Range: 1.6864. Min Range: -1.6864

Max Act: 1.2311. Min Act: -0.0000

Data Index: 1500387 (Python Code)

Max Activating Token Index: 200

Text #17

Max Range: 1.6864. Min Range: -1.6864

Max Act: 1.2713. Min Act: -0.0000

Data Index: 1521780 (Python Code)

Max Activating Token Index: 836

Text #18

Max Range: 1.6864. Min Range: -1.6864

Max Act: 1.3121. Min Act: -0.0000

Data Index: 1642104 (Python Code)

Max Activating Token Index: 507

Text #19

Max Range: 1.6864. Min Range: -1.6864

Max Act: 1.3008. Min Act: -0.0000

Data Index: 1398851 (Python Code)

Max Activating Token Index: 346