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

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

Neuron 3691 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4447. Min Range: -0.4447

Max Act: 0.4447. Min Act: -0.0001

Data Index: 1333076 (C4 (Web Text))

Max Activating Token Index: 389

Text #1

Max Range: 0.4447. Min Range: -0.4447

Max Act: 0.4121. Min Act: -0.0001

Data Index: 98409 (C4 (Web Text))

Max Activating Token Index: 326

Text #2

Max Range: 0.4447. Min Range: -0.4447

Max Act: 0.4063. Min Act: -0.0001

Data Index: 803380 (C4 (Web Text))

Max Activating Token Index: 815

Text #3

Max Range: 0.4447. Min Range: -0.4447

Max Act: 0.3772. Min Act: -0.0001

Data Index: 627881 (C4 (Web Text))

Max Activating Token Index: 322

Text #4

Max Range: 0.4447. Min Range: -0.4447

Max Act: 0.3900. Min Act: -0.0001

Data Index: 1091007 (C4 (Web Text))

Max Activating Token Index: 264

Text #5

Max Range: 0.4447. Min Range: -0.4447

Max Act: 0.3803. Min Act: -0.0001

Data Index: 1105272 (C4 (Web Text))

Max Activating Token Index: 346

Text #6

Max Range: 0.4447. Min Range: -0.4447

Max Act: 0.3816. Min Act: -0.0001

Data Index: 345991 (C4 (Web Text))

Max Activating Token Index: 757

Text #7

Max Range: 0.4447. Min Range: -0.4447

Max Act: 0.3942. Min Act: -0.0001

Data Index: 1224153 (C4 (Web Text))

Max Activating Token Index: 736

Text #8

Max Range: 0.4447. Min Range: -0.4447

Max Act: 0.3571. Min Act: -0.0001

Data Index: 399116 (C4 (Web Text))

Max Activating Token Index: 235

Text #9

Max Range: 0.4447. Min Range: -0.4447

Max Act: 0.3670. Min Act: -0.0001

Data Index: 949453 (C4 (Web Text))

Max Activating Token Index: 91

Text #10

Max Range: 0.4447. Min Range: -0.4447

Max Act: 0.3463. Min Act: -0.0001

Data Index: 710919 (C4 (Web Text))

Max Activating Token Index: 176

Text #11

Max Range: 0.4447. Min Range: -0.4447

Max Act: 0.3438. Min Act: -0.0001

Data Index: 1203283 (C4 (Web Text))

Max Activating Token Index: 917

Text #12

Max Range: 0.4447. Min Range: -0.4447

Max Act: 0.3343. Min Act: -0.0001

Data Index: 458264 (C4 (Web Text))

Max Activating Token Index: 713

Text #13

Max Range: 0.4447. Min Range: -0.4447

Max Act: 0.3197. Min Act: -0.0001

Data Index: 590750 (C4 (Web Text))

Max Activating Token Index: 693

Text #14

Max Range: 0.4447. Min Range: -0.4447

Max Act: 0.3491. Min Act: -0.0001

Data Index: 644556 (C4 (Web Text))

Max Activating Token Index: 800

Text #15

Max Range: 0.4447. Min Range: -0.4447

Max Act: 0.3361. Min Act: -0.0001

Data Index: 1279053 (C4 (Web Text))

Max Activating Token Index: 834

Text #16

Max Range: 0.4447. Min Range: -0.4447

Max Act: 0.3305. Min Act: -0.0001

Data Index: 1190529 (C4 (Web Text))

Max Activating Token Index: 211

Text #17

Max Range: 0.4447. Min Range: -0.4447

Max Act: 0.3331. Min Act: -0.0001

Data Index: 823420 (C4 (Web Text))

Max Activating Token Index: 947

Text #18

Max Range: 0.4447. Min Range: -0.4447

Max Act: 0.3324. Min Act: -0.0001

Data Index: 277719 (C4 (Web Text))

Max Activating Token Index: 770

Text #19

Max Range: 0.4447. Min Range: -0.4447

Max Act: 0.3435. Min Act: -0.0001

Data Index: 1025273 (C4 (Web Text))

Max Activating Token Index: 980