Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4181 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.3726. Min Range: -0.3726

Max Act: 0.3726. Min Act: -0.0002

Data Index: 495106 (C4 (Web Text))

Max Activating Token Index: 300

Text #1

Max Range: 0.3726. Min Range: -0.3726

Max Act: 0.3558. Min Act: -0.0002

Data Index: 707987 (C4 (Web Text))

Max Activating Token Index: 409

Text #2

Max Range: 0.3726. Min Range: -0.3726

Max Act: 0.3310. Min Act: -0.0002

Data Index: 310567 (C4 (Web Text))

Max Activating Token Index: 839

Text #3

Max Range: 0.3726. Min Range: -0.3726

Max Act: 0.3486. Min Act: -0.0002

Data Index: 37766 (C4 (Web Text))

Max Activating Token Index: 34

Text #4

Max Range: 0.3726. Min Range: -0.3726

Max Act: 0.3351. Min Act: -0.0002

Data Index: 886362 (C4 (Web Text))

Max Activating Token Index: 135

Text #5

Max Range: 0.3726. Min Range: -0.3726

Max Act: 0.3249. Min Act: -0.0002

Data Index: 1242095 (C4 (Web Text))

Max Activating Token Index: 24

Text #6

Max Range: 0.3726. Min Range: -0.3726

Max Act: 0.3268. Min Act: -0.0002

Data Index: 473109 (C4 (Web Text))

Max Activating Token Index: 233

Text #7

Max Range: 0.3726. Min Range: -0.3726

Max Act: 0.3424. Min Act: -0.0002

Data Index: 714089 (C4 (Web Text))

Max Activating Token Index: 73

Text #8

Max Range: 0.3726. Min Range: -0.3726

Max Act: 0.3458. Min Act: -0.0002

Data Index: 637774 (C4 (Web Text))

Max Activating Token Index: 352

Text #9

Max Range: 0.3726. Min Range: -0.3726

Max Act: 0.3293. Min Act: -0.0002

Data Index: 930054 (C4 (Web Text))

Max Activating Token Index: 944

Text #10

Max Range: 0.3726. Min Range: -0.3726

Max Act: 0.3024. Min Act: -0.0002

Data Index: 770585 (C4 (Web Text))

Max Activating Token Index: 26

Text #11

Max Range: 0.3726. Min Range: -0.3726

Max Act: 0.3252. Min Act: -0.0002

Data Index: 717564 (C4 (Web Text))

Max Activating Token Index: 191

Text #12

Max Range: 0.3726. Min Range: -0.3726

Max Act: 0.3135. Min Act: -0.0002

Data Index: 1083870 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 0.3726. Min Range: -0.3726

Max Act: 0.3050. Min Act: -0.0002

Data Index: 6902 (C4 (Web Text))

Max Activating Token Index: 586

Text #14

Max Range: 0.3726. Min Range: -0.3726

Max Act: 0.3007. Min Act: -0.0002

Data Index: 1229165 (C4 (Web Text))

Max Activating Token Index: 957

Text #15

Max Range: 0.3726. Min Range: -0.3726

Max Act: 0.3030. Min Act: -0.0002

Data Index: 1124209 (C4 (Web Text))

Max Activating Token Index: 53

Text #16

Max Range: 0.3726. Min Range: -0.3726

Max Act: 0.3108. Min Act: -0.0002

Data Index: 624391 (C4 (Web Text))

Max Activating Token Index: 1013

Text #17

Max Range: 0.3726. Min Range: -0.3726

Max Act: 0.2942. Min Act: -0.0002

Data Index: 36866 (C4 (Web Text))

Max Activating Token Index: 881

Text #18

Max Range: 0.3726. Min Range: -0.3726

Max Act: 0.3206. Min Act: -0.0002

Data Index: 423641 (C4 (Web Text))

Max Activating Token Index: 701

Text #19

Max Range: 0.3726. Min Range: -0.3726

Max Act: 0.2943. Min Act: -0.0002

Data Index: 515922 (C4 (Web Text))

Max Activating Token Index: 1006