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

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

Neuron 506 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: 0.4767. Min Range: -0.4767

Max Act: 0.4767. Min Act: -0.0001

Data Index: 1043784 (C4 (Web Text))

Max Activating Token Index: 223

Text #1

Max Range: 0.4767. Min Range: -0.4767

Max Act: 0.4265. Min Act: -0.0001

Data Index: 1110537 (C4 (Web Text))

Max Activating Token Index: 385

Text #2

Max Range: 0.4767. Min Range: -0.4767

Max Act: 0.4346. Min Act: -0.0001

Data Index: 42447 (C4 (Web Text))

Max Activating Token Index: 836

Text #3

Max Range: 0.4767. Min Range: -0.4767

Max Act: 0.4395. Min Act: -0.0001

Data Index: 871601 (C4 (Web Text))

Max Activating Token Index: 870

Text #4

Max Range: 0.4767. Min Range: -0.4767

Max Act: 0.4387. Min Act: -0.0001

Data Index: 140212 (C4 (Web Text))

Max Activating Token Index: 30

Text #5

Max Range: 0.4767. Min Range: -0.4767

Max Act: 0.4347. Min Act: -0.0001

Data Index: 912825 (C4 (Web Text))

Max Activating Token Index: 62

Text #6

Max Range: 0.4767. Min Range: -0.4767

Max Act: 0.4331. Min Act: -0.0001

Data Index: 348940 (C4 (Web Text))

Max Activating Token Index: 622

Text #7

Max Range: 0.4767. Min Range: -0.4767

Max Act: 0.4327. Min Act: -0.0001

Data Index: 995458 (C4 (Web Text))

Max Activating Token Index: 60

Text #8

Max Range: 0.4767. Min Range: -0.4767

Max Act: 0.4177. Min Act: -0.0001

Data Index: 405827 (C4 (Web Text))

Max Activating Token Index: 654

Text #9

Max Range: 0.4767. Min Range: -0.4767

Max Act: 0.4321. Min Act: -0.0001

Data Index: 1194117 (C4 (Web Text))

Max Activating Token Index: 518

Text #10

Max Range: 0.4767. Min Range: -0.4767

Max Act: 0.3987. Min Act: -0.0001

Data Index: 1186969 (C4 (Web Text))

Max Activating Token Index: 890

Text #11

Max Range: 0.4767. Min Range: -0.4767

Max Act: 0.4295. Min Act: -0.0001

Data Index: 33804 (C4 (Web Text))

Max Activating Token Index: 668

Text #12

Max Range: 0.4767. Min Range: -0.4767

Max Act: 0.4011. Min Act: -0.0001

Data Index: 876670 (C4 (Web Text))

Max Activating Token Index: 356

Text #13

Max Range: 0.4767. Min Range: -0.4767

Max Act: 0.4277. Min Act: -0.0001

Data Index: 293962 (C4 (Web Text))

Max Activating Token Index: 143

Text #14

Max Range: 0.4767. Min Range: -0.4767

Max Act: 0.4234. Min Act: -0.0001

Data Index: 959975 (C4 (Web Text))

Max Activating Token Index: 198

Text #15

Max Range: 0.4767. Min Range: -0.4767

Max Act: 0.4038. Min Act: -0.0001

Data Index: 532876 (C4 (Web Text))

Max Activating Token Index: 720

Text #16

Max Range: 0.4767. Min Range: -0.4767

Max Act: 0.4049. Min Act: -0.0001

Data Index: 399161 (C4 (Web Text))

Max Activating Token Index: 801

Text #17

Max Range: 0.4767. Min Range: -0.4767

Max Act: 0.4025. Min Act: -0.0001

Data Index: 51075 (C4 (Web Text))

Max Activating Token Index: 14

Text #18

Max Range: 0.4767. Min Range: -0.4767

Max Act: 0.4150. Min Act: -0.0001

Data Index: 46117 (C4 (Web Text))

Max Activating Token Index: 509

Text #19

Max Range: 0.4767. Min Range: -0.4767

Max Act: 0.3917. Min Act: -0.0001

Data Index: 1193752 (C4 (Web Text))

Max Activating Token Index: 212