Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 885 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.6194. Min Range: -0.6194

Max Act: 0.6194. Min Act: -0.0001

Data Index: 383668 (C4 (Web Text))

Max Activating Token Index: 705

Text #1

Max Range: 0.6194. Min Range: -0.6194

Max Act: 0.5799. Min Act: -0.0001

Data Index: 284578 (C4 (Web Text))

Max Activating Token Index: 674

Text #2

Max Range: 0.6194. Min Range: -0.6194

Max Act: 0.5424. Min Act: -0.0001

Data Index: 1123121 (C4 (Web Text))

Max Activating Token Index: 653

Text #3

Max Range: 0.6194. Min Range: -0.6194

Max Act: 0.4970. Min Act: -0.0001

Data Index: 538098 (C4 (Web Text))

Max Activating Token Index: 523

Text #4

Max Range: 0.6194. Min Range: -0.6194

Max Act: 0.5294. Min Act: -0.0001

Data Index: 540843 (C4 (Web Text))

Max Activating Token Index: 400

Text #5

Max Range: 0.6194. Min Range: -0.6194

Max Act: 0.4989. Min Act: -0.0001

Data Index: 868679 (C4 (Web Text))

Max Activating Token Index: 737

Text #6

Max Range: 0.6194. Min Range: -0.6194

Max Act: 0.4923. Min Act: -0.0001

Data Index: 540889 (C4 (Web Text))

Max Activating Token Index: 481

Text #7

Max Range: 0.6194. Min Range: -0.6194

Max Act: 0.4790. Min Act: -0.0001

Data Index: 295675 (C4 (Web Text))

Max Activating Token Index: 605

Text #8

Max Range: 0.6194. Min Range: -0.6194

Max Act: 0.4200. Min Act: -0.0001

Data Index: 978950 (C4 (Web Text))

Max Activating Token Index: 874

Text #9

Max Range: 0.6194. Min Range: -0.6194

Max Act: 0.4020. Min Act: -0.0001

Data Index: 877595 (C4 (Web Text))

Max Activating Token Index: 885

Text #10

Max Range: 0.6194. Min Range: -0.6194

Max Act: 0.4767. Min Act: -0.0001

Data Index: 509689 (C4 (Web Text))

Max Activating Token Index: 700

Text #11

Max Range: 0.6194. Min Range: -0.6194

Max Act: 0.4749. Min Act: -0.0001

Data Index: 1026691 (C4 (Web Text))

Max Activating Token Index: 604

Text #12

Max Range: 0.6194. Min Range: -0.6194

Max Act: 0.4447. Min Act: -0.0001

Data Index: 491506 (C4 (Web Text))

Max Activating Token Index: 159

Text #13

Max Range: 0.6194. Min Range: -0.6194

Max Act: 0.4515. Min Act: -0.0001

Data Index: 996937 (C4 (Web Text))

Max Activating Token Index: 285

Text #14

Max Range: 0.6194. Min Range: -0.6194

Max Act: 0.4331. Min Act: -0.0001

Data Index: 71985 (C4 (Web Text))

Max Activating Token Index: 794

Text #15

Max Range: 0.6194. Min Range: -0.6194

Max Act: 0.4295. Min Act: -0.0001

Data Index: 924898 (C4 (Web Text))

Max Activating Token Index: 420

Text #16

Max Range: 0.6194. Min Range: -0.6194

Max Act: 0.4214. Min Act: -0.0001

Data Index: 1013090 (C4 (Web Text))

Max Activating Token Index: 235

Text #17

Max Range: 0.6194. Min Range: -0.6194

Max Act: 0.4699. Min Act: -0.0001

Data Index: 854410 (C4 (Web Text))

Max Activating Token Index: 998

Text #18

Max Range: 0.6194. Min Range: -0.6194

Max Act: 0.4361. Min Act: -0.0001

Data Index: 72334 (C4 (Web Text))

Max Activating Token Index: 412

Text #19

Max Range: 0.6194. Min Range: -0.6194

Max Act: 0.4524. Min Act: -0.0001

Data Index: 101080 (C4 (Web Text))

Max Activating Token Index: 697