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

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

Neuron 1573 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6128. Min Range: -0.6128

Max Act: 0.6128. Min Act: -0.0001

Data Index: 79877 (C4 (Web Text))

Max Activating Token Index: 391

Text #1

Max Range: 0.6128. Min Range: -0.6128

Max Act: 0.5918. Min Act: -0.0001

Data Index: 657185 (C4 (Web Text))

Max Activating Token Index: 673

Text #2

Max Range: 0.6128. Min Range: -0.6128

Max Act: 0.5597. Min Act: -0.0001

Data Index: 1288837 (C4 (Web Text))

Max Activating Token Index: 864

Text #3

Max Range: 0.6128. Min Range: -0.6128

Max Act: 0.5570. Min Act: -0.0001

Data Index: 874258 (C4 (Web Text))

Max Activating Token Index: 123

Text #4

Max Range: 0.6128. Min Range: -0.6128

Max Act: 0.5450. Min Act: -0.0001

Data Index: 1056442 (C4 (Web Text))

Max Activating Token Index: 129

Text #5

Max Range: 0.6128. Min Range: -0.6128

Max Act: 0.5287. Min Act: -0.0001

Data Index: 164508 (C4 (Web Text))

Max Activating Token Index: 854

Text #6

Max Range: 0.6128. Min Range: -0.6128

Max Act: 0.5385. Min Act: -0.0001

Data Index: 766392 (C4 (Web Text))

Max Activating Token Index: 325

Text #7

Max Range: 0.6128. Min Range: -0.6128

Max Act: 0.4963. Min Act: -0.0001

Data Index: 630533 (C4 (Web Text))

Max Activating Token Index: 513

Text #8

Max Range: 0.6128. Min Range: -0.6128

Max Act: 0.5212. Min Act: -0.0001

Data Index: 660432 (C4 (Web Text))

Max Activating Token Index: 387

Text #9

Max Range: 0.6128. Min Range: -0.6128

Max Act: 0.4988. Min Act: -0.0001

Data Index: 268601 (C4 (Web Text))

Max Activating Token Index: 8

Text #10

Max Range: 0.6128. Min Range: -0.6128

Max Act: 0.5224. Min Act: -0.0001

Data Index: 159237 (C4 (Web Text))

Max Activating Token Index: 234

Text #11

Max Range: 0.6128. Min Range: -0.6128

Max Act: 0.5124. Min Act: -0.0001

Data Index: 411770 (C4 (Web Text))

Max Activating Token Index: 113

Text #12

Max Range: 0.6128. Min Range: -0.6128

Max Act: 0.4969. Min Act: -0.0001

Data Index: 1167012 (C4 (Web Text))

Max Activating Token Index: 40

Text #13

Max Range: 0.6128. Min Range: -0.6128

Max Act: 0.4756. Min Act: -0.0001

Data Index: 1113714 (C4 (Web Text))

Max Activating Token Index: 415

Text #14

Max Range: 0.6128. Min Range: -0.6128

Max Act: 0.4751. Min Act: -0.0001

Data Index: 501810 (C4 (Web Text))

Max Activating Token Index: 19

Text #15

Max Range: 0.6128. Min Range: -0.6128

Max Act: 0.4885. Min Act: -0.0001

Data Index: 210431 (C4 (Web Text))

Max Activating Token Index: 35

Text #16

Max Range: 0.6128. Min Range: -0.6128

Max Act: 0.4530. Min Act: -0.0001

Data Index: 394957 (C4 (Web Text))

Max Activating Token Index: 661

Text #17

Max Range: 0.6128. Min Range: -0.6128

Max Act: 0.4811. Min Act: -0.0001

Data Index: 620589 (C4 (Web Text))

Max Activating Token Index: 438

Text #18

Max Range: 0.6128. Min Range: -0.6128

Max Act: 0.4941. Min Act: -0.0001

Data Index: 590254 (C4 (Web Text))

Max Activating Token Index: 166

Text #19

Max Range: 0.6128. Min Range: -0.6128

Max Act: 0.5081. Min Act: -0.0001

Data Index: 612885 (C4 (Web Text))

Max Activating Token Index: 887