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

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

Neuron 3784 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4697. Min Range: -0.4697

Max Act: 0.3848. Min Act: -0.0002

Data Index: 1329354 (C4 (Web Text))

Max Activating Token Index: 537

Text #1

Max Range: 0.4697. Min Range: -0.4697

Max Act: 0.4258. Min Act: -0.0001

Data Index: 117387 (C4 (Web Text))

Max Activating Token Index: 351

Text #2

Max Range: 0.4697. Min Range: -0.4697

Max Act: 0.4159. Min Act: -0.0002

Data Index: 17956 (C4 (Web Text))

Max Activating Token Index: 548

Text #3

Max Range: 0.4697. Min Range: -0.4697

Max Act: 0.4350. Min Act: -0.0002

Data Index: 382096 (C4 (Web Text))

Max Activating Token Index: 182

Text #4

Max Range: 0.4697. Min Range: -0.4697

Max Act: 0.3978. Min Act: -0.0002

Data Index: 1027093 (C4 (Web Text))

Max Activating Token Index: 523

Text #5

Max Range: 0.4697. Min Range: -0.4697

Max Act: 0.4280. Min Act: -0.0002

Data Index: 102477 (C4 (Web Text))

Max Activating Token Index: 40

Text #6

Max Range: 0.4697. Min Range: -0.4697

Max Act: 0.4160. Min Act: -0.0002

Data Index: 1046506 (C4 (Web Text))

Max Activating Token Index: 866

Text #7

Max Range: 0.4697. Min Range: -0.4697

Max Act: 0.4113. Min Act: -0.0002

Data Index: 481708 (C4 (Web Text))

Max Activating Token Index: 41

Text #8

Max Range: 0.4697. Min Range: -0.4697

Max Act: 0.4465. Min Act: -0.0002

Data Index: 2546 (C4 (Web Text))

Max Activating Token Index: 217

Text #9

Max Range: 0.4697. Min Range: -0.4697

Max Act: 0.4201. Min Act: -0.0002

Data Index: 1282581 (C4 (Web Text))

Max Activating Token Index: 384

Text #10

Max Range: 0.4697. Min Range: -0.4697

Max Act: 0.3937. Min Act: -0.0001

Data Index: 1116610 (C4 (Web Text))

Max Activating Token Index: 1020

Text #11

Max Range: 0.4697. Min Range: -0.4697

Max Act: 0.4313. Min Act: -0.0002

Data Index: 717298 (C4 (Web Text))

Max Activating Token Index: 925

Text #12

Max Range: 0.4697. Min Range: -0.4697

Max Act: 0.4209. Min Act: -0.0002

Data Index: 474724 (C4 (Web Text))

Max Activating Token Index: 325

Text #13

Max Range: 0.4697. Min Range: -0.4697

Max Act: 0.4007. Min Act: -0.0002

Data Index: 718335 (C4 (Web Text))

Max Activating Token Index: 39

Text #14

Max Range: 0.4697. Min Range: -0.4697

Max Act: 0.4287. Min Act: -0.0002

Data Index: 1022661 (C4 (Web Text))

Max Activating Token Index: 80

Text #15

Max Range: 0.4697. Min Range: -0.4697

Max Act: 0.4022. Min Act: -0.0002

Data Index: 357485 (C4 (Web Text))

Max Activating Token Index: 67

Text #16

Max Range: 0.4697. Min Range: -0.4697

Max Act: 0.3857. Min Act: -0.0002

Data Index: 58049 (C4 (Web Text))

Max Activating Token Index: 192

Text #17

Max Range: 0.4697. Min Range: -0.4697

Max Act: 0.3937. Min Act: -0.0002

Data Index: 1236989 (C4 (Web Text))

Max Activating Token Index: 24

Text #18

Max Range: 0.4697. Min Range: -0.4697

Max Act: 0.4697. Min Act: -0.0002

Data Index: 1062205 (C4 (Web Text))

Max Activating Token Index: 988

Text #19

Max Range: 0.4697. Min Range: -0.4697

Max Act: 0.4223. Min Act: -0.0002

Data Index: 1082792 (C4 (Web Text))

Max Activating Token Index: 62