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

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

Neuron 1324 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8641. Min Range: -0.8641

Max Act: 0.8641. Min Act: -0.0000

Data Index: 750214 (C4 (Web Text))

Max Activating Token Index: 310

Text #1

Max Range: 0.8641. Min Range: -0.8641

Max Act: 0.8372. Min Act: -0.0000

Data Index: 878535 (C4 (Web Text))

Max Activating Token Index: 581

Text #2

Max Range: 0.8641. Min Range: -0.8641

Max Act: 0.7662. Min Act: -0.0000

Data Index: 661377 (C4 (Web Text))

Max Activating Token Index: 772

Text #3

Max Range: 0.8641. Min Range: -0.8641

Max Act: 0.7228. Min Act: -0.0000

Data Index: 215473 (C4 (Web Text))

Max Activating Token Index: 404

Text #4

Max Range: 0.8641. Min Range: -0.8641

Max Act: 0.7694. Min Act: -0.0000

Data Index: 609014 (C4 (Web Text))

Max Activating Token Index: 965

Text #5

Max Range: 0.8641. Min Range: -0.8641

Max Act: 0.6865. Min Act: -0.0000

Data Index: 48149 (C4 (Web Text))

Max Activating Token Index: 327

Text #6

Max Range: 0.8641. Min Range: -0.8641

Max Act: 0.6890. Min Act: -0.0000

Data Index: 426908 (C4 (Web Text))

Max Activating Token Index: 156

Text #7

Max Range: 0.8641. Min Range: -0.8641

Max Act: 0.6593. Min Act: -0.0000

Data Index: 780017 (C4 (Web Text))

Max Activating Token Index: 935

Text #8

Max Range: 0.8641. Min Range: -0.8641

Max Act: 0.6311. Min Act: -0.0000

Data Index: 81479 (C4 (Web Text))

Max Activating Token Index: 962

Text #9

Max Range: 0.8641. Min Range: -0.8641

Max Act: 0.6444. Min Act: -0.0000

Data Index: 11109 (C4 (Web Text))

Max Activating Token Index: 59

Text #10

Max Range: 0.8641. Min Range: -0.8641

Max Act: 0.6816. Min Act: -0.0000

Data Index: 570205 (C4 (Web Text))

Max Activating Token Index: 545

Text #11

Max Range: 0.8641. Min Range: -0.8641

Max Act: 0.6523. Min Act: -0.0000

Data Index: 821789 (C4 (Web Text))

Max Activating Token Index: 191

Text #12

Max Range: 0.8641. Min Range: -0.8641

Max Act: 0.6326. Min Act: -0.0000

Data Index: 438156 (C4 (Web Text))

Max Activating Token Index: 222

Text #13

Max Range: 0.8641. Min Range: -0.8641

Max Act: 0.6466. Min Act: -0.0000

Data Index: 524580 (C4 (Web Text))

Max Activating Token Index: 284

Text #14

Max Range: 0.8641. Min Range: -0.8641

Max Act: 0.6290. Min Act: -0.0000

Data Index: 1140034 (C4 (Web Text))

Max Activating Token Index: 904

Text #15

Max Range: 0.8641. Min Range: -0.8641

Max Act: 0.6434. Min Act: -0.0000

Data Index: 862216 (C4 (Web Text))

Max Activating Token Index: 8

Text #16

Max Range: 0.8641. Min Range: -0.8641

Max Act: 0.6247. Min Act: -0.0000

Data Index: 304154 (C4 (Web Text))

Max Activating Token Index: 40

Text #17

Max Range: 0.8641. Min Range: -0.8641

Max Act: 0.6573. Min Act: -0.0000

Data Index: 660120 (C4 (Web Text))

Max Activating Token Index: 763

Text #18

Max Range: 0.8641. Min Range: -0.8641

Max Act: 0.6044. Min Act: -0.0000

Data Index: 1016902 (C4 (Web Text))

Max Activating Token Index: 356

Text #19

Max Range: 0.8641. Min Range: -0.8641

Max Act: 0.6424. Min Act: -0.0000

Data Index: 670079 (C4 (Web Text))

Max Activating Token Index: 374