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

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

Neuron 2642 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: 3.3618. Min Range: -3.3618

Max Act: 3.3618. Min Act: -0.0001

Data Index: 1188118 (C4 (Web Text))

Max Activating Token Index: 79

Text #1

Max Range: 3.3618. Min Range: -3.3618

Max Act: 3.1895. Min Act: -0.0001

Data Index: 205919 (C4 (Web Text))

Max Activating Token Index: 828

Text #2

Max Range: 3.3618. Min Range: -3.3618

Max Act: 3.2236. Min Act: -0.0001

Data Index: 1314546 (C4 (Web Text))

Max Activating Token Index: 842

Text #3

Max Range: 3.3618. Min Range: -3.3618

Max Act: 2.9733. Min Act: -0.0001

Data Index: 1204535 (C4 (Web Text))

Max Activating Token Index: 390

Text #4

Max Range: 3.3618. Min Range: -3.3618

Max Act: 3.0827. Min Act: -0.0001

Data Index: 1129939 (C4 (Web Text))

Max Activating Token Index: 65

Text #5

Max Range: 3.3618. Min Range: -3.3618

Max Act: 2.9187. Min Act: -0.0001

Data Index: 837031 (C4 (Web Text))

Max Activating Token Index: 33

Text #6

Max Range: 3.3618. Min Range: -3.3618

Max Act: 3.0070. Min Act: -0.0001

Data Index: 874320 (C4 (Web Text))

Max Activating Token Index: 960

Text #7

Max Range: 3.3618. Min Range: -3.3618

Max Act: 2.8571. Min Act: -0.0001

Data Index: 98585 (C4 (Web Text))

Max Activating Token Index: 73

Text #8

Max Range: 3.3618. Min Range: -3.3618

Max Act: 3.1197. Min Act: -0.0001

Data Index: 756940 (C4 (Web Text))

Max Activating Token Index: 294

Text #9

Max Range: 3.3618. Min Range: -3.3618

Max Act: 3.0845. Min Act: -0.0001

Data Index: 458674 (C4 (Web Text))

Max Activating Token Index: 508

Text #10

Max Range: 3.3618. Min Range: -3.3618

Max Act: 2.8392. Min Act: -0.0001

Data Index: 519801 (C4 (Web Text))

Max Activating Token Index: 85

Text #11

Max Range: 3.3618. Min Range: -3.3618

Max Act: 2.7032. Min Act: -0.0001

Data Index: 711940 (C4 (Web Text))

Max Activating Token Index: 246

Text #12

Max Range: 3.3618. Min Range: -3.3618

Max Act: 2.6933. Min Act: -0.0001

Data Index: 1003026 (C4 (Web Text))

Max Activating Token Index: 400

Text #13

Max Range: 3.3618. Min Range: -3.3618

Max Act: 2.8000. Min Act: -0.0001

Data Index: 883183 (C4 (Web Text))

Max Activating Token Index: 806

Text #14

Max Range: 3.3618. Min Range: -3.3618

Max Act: 2.9044. Min Act: -0.0001

Data Index: 806210 (C4 (Web Text))

Max Activating Token Index: 874

Text #15

Max Range: 3.3618. Min Range: -3.3618

Max Act: 2.6456. Min Act: -0.0001

Data Index: 451819 (C4 (Web Text))

Max Activating Token Index: 921

Text #16

Max Range: 3.3618. Min Range: -3.3618

Max Act: 2.6376. Min Act: -0.0001

Data Index: 220176 (C4 (Web Text))

Max Activating Token Index: 869

Text #17

Max Range: 3.3618. Min Range: -3.3618

Max Act: 2.7625. Min Act: -0.0001

Data Index: 885737 (C4 (Web Text))

Max Activating Token Index: 936

Text #18

Max Range: 3.3618. Min Range: -3.3618

Max Act: 2.5949. Min Act: -0.0001

Data Index: 39147 (C4 (Web Text))

Max Activating Token Index: 142

Text #19

Max Range: 3.3618. Min Range: -3.3618

Max Act: 2.4775. Min Act: -0.0001

Data Index: 767660 (C4 (Web Text))

Max Activating Token Index: 707