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

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

Neuron 107 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3128. Min Range: -1.3128

Max Act: 1.3128. Min Act: -0.0003

Data Index: 1310544 (C4 (Web Text))

Max Activating Token Index: 180

Text #1

Max Range: 1.3128. Min Range: -1.3128

Max Act: 1.0459. Min Act: -0.0003

Data Index: 718096 (C4 (Web Text))

Max Activating Token Index: 1017

Text #2

Max Range: 1.3128. Min Range: -1.3128

Max Act: 1.0743. Min Act: -0.0003

Data Index: 988358 (C4 (Web Text))

Max Activating Token Index: 622

Text #3

Max Range: 1.3128. Min Range: -1.3128

Max Act: 1.0353. Min Act: -0.0003

Data Index: 905503 (C4 (Web Text))

Max Activating Token Index: 1000

Text #4

Max Range: 1.3128. Min Range: -1.3128

Max Act: 0.9481. Min Act: -0.0003

Data Index: 416162 (C4 (Web Text))

Max Activating Token Index: 45

Text #5

Max Range: 1.3128. Min Range: -1.3128

Max Act: 0.9675. Min Act: -0.0003

Data Index: 1105325 (C4 (Web Text))

Max Activating Token Index: 86

Text #6

Max Range: 1.3128. Min Range: -1.3128

Max Act: 0.8569. Min Act: -0.0003

Data Index: 190941 (C4 (Web Text))

Max Activating Token Index: 769

Text #7

Max Range: 1.3128. Min Range: -1.3128

Max Act: 1.0042. Min Act: -0.0003

Data Index: 1329253 (C4 (Web Text))

Max Activating Token Index: 726

Text #8

Max Range: 1.3128. Min Range: -1.3128

Max Act: 0.8907. Min Act: -0.0003

Data Index: 1140640 (C4 (Web Text))

Max Activating Token Index: 46

Text #9

Max Range: 1.3128. Min Range: -1.3128

Max Act: 0.8785. Min Act: -0.0003

Data Index: 876871 (C4 (Web Text))

Max Activating Token Index: 135

Text #10

Max Range: 1.3128. Min Range: -1.3128

Max Act: 0.7948. Min Act: -0.0003

Data Index: 413407 (C4 (Web Text))

Max Activating Token Index: 281

Text #11

Max Range: 1.3128. Min Range: -1.3128

Max Act: 0.8452. Min Act: -0.0003

Data Index: 61004 (C4 (Web Text))

Max Activating Token Index: 1013

Text #12

Max Range: 1.3128. Min Range: -1.3128

Max Act: 0.8938. Min Act: -0.0003

Data Index: 1170773 (C4 (Web Text))

Max Activating Token Index: 857

Text #13

Max Range: 1.3128. Min Range: -1.3128

Max Act: 0.8785. Min Act: -0.0003

Data Index: 1143267 (C4 (Web Text))

Max Activating Token Index: 894

Text #14

Max Range: 1.3128. Min Range: -1.3128

Max Act: 0.8194. Min Act: -0.0003

Data Index: 1066070 (C4 (Web Text))

Max Activating Token Index: 595

Text #15

Max Range: 1.3128. Min Range: -1.3128

Max Act: 0.8429. Min Act: -0.0003

Data Index: 1189671 (C4 (Web Text))

Max Activating Token Index: 920

Text #16

Max Range: 1.3128. Min Range: -1.3128

Max Act: 0.8007. Min Act: -0.0003

Data Index: 595874 (C4 (Web Text))

Max Activating Token Index: 608

Text #17

Max Range: 1.3128. Min Range: -1.3128

Max Act: 0.7659. Min Act: -0.0003

Data Index: 552068 (C4 (Web Text))

Max Activating Token Index: 475

Text #18

Max Range: 1.3128. Min Range: -1.3128

Max Act: 0.8403. Min Act: -0.0003

Data Index: 795026 (C4 (Web Text))

Max Activating Token Index: 74

Text #19

Max Range: 1.3128. Min Range: -1.3128

Max Act: 0.8298. Min Act: -0.0002

Data Index: 133383 (C4 (Web Text))

Max Activating Token Index: 49