Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1068 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.7126. Min Range: -0.7126

Max Act: 0.7126. Min Act: -0.0000

Data Index: 620228 (C4 (Web Text))

Max Activating Token Index: 300

Text #1

Max Range: 0.7126. Min Range: -0.7126

Max Act: 0.7100. Min Act: 0.0001

Data Index: 193357 (C4 (Web Text))

Max Activating Token Index: 89

Text #2

Max Range: 0.7126. Min Range: -0.7126

Max Act: 0.6382. Min Act: 0.0000

Data Index: 1034179 (C4 (Web Text))

Max Activating Token Index: 683

Text #3

Max Range: 0.7126. Min Range: -0.7126

Max Act: 0.6325. Min Act: 0.0000

Data Index: 1111714 (C4 (Web Text))

Max Activating Token Index: 402

Text #4

Max Range: 0.7126. Min Range: -0.7126

Max Act: 0.5707. Min Act: 0.0002

Data Index: 1136725 (C4 (Web Text))

Max Activating Token Index: 12

Text #5

Max Range: 0.7126. Min Range: -0.7126

Max Act: 0.5702. Min Act: -0.0000

Data Index: 577260 (C4 (Web Text))

Max Activating Token Index: 586

Text #6

Max Range: 0.7126. Min Range: -0.7126

Max Act: 0.5517. Min Act: -0.0000

Data Index: 408145 (C4 (Web Text))

Max Activating Token Index: 47

Text #7

Max Range: 0.7126. Min Range: -0.7126

Max Act: 0.5378. Min Act: -0.0000

Data Index: 827069 (C4 (Web Text))

Max Activating Token Index: 479

Text #8

Max Range: 0.7126. Min Range: -0.7126

Max Act: 0.5215. Min Act: 0.0001

Data Index: 1325426 (C4 (Web Text))

Max Activating Token Index: 940

Text #9

Max Range: 0.7126. Min Range: -0.7126

Max Act: 0.5324. Min Act: -0.0000

Data Index: 1313020 (C4 (Web Text))

Max Activating Token Index: 378

Text #10

Max Range: 0.7126. Min Range: -0.7126

Max Act: 0.5254. Min Act: -0.0000

Data Index: 418924 (C4 (Web Text))

Max Activating Token Index: 333

Text #11

Max Range: 0.7126. Min Range: -0.7126

Max Act: 0.5073. Min Act: -0.0000

Data Index: 758465 (C4 (Web Text))

Max Activating Token Index: 51

Text #12

Max Range: 0.7126. Min Range: -0.7126

Max Act: 0.5068. Min Act: -0.0000

Data Index: 1058120 (C4 (Web Text))

Max Activating Token Index: 883

Text #13

Max Range: 0.7126. Min Range: -0.7126

Max Act: 0.5058. Min Act: -0.0000

Data Index: 322598 (C4 (Web Text))

Max Activating Token Index: 497

Text #14

Max Range: 0.7126. Min Range: -0.7126

Max Act: 0.5180. Min Act: -0.0000

Data Index: 616287 (C4 (Web Text))

Max Activating Token Index: 693

Text #15

Max Range: 0.7126. Min Range: -0.7126

Max Act: 0.4817. Min Act: -0.0000

Data Index: 214047 (C4 (Web Text))

Max Activating Token Index: 343

Text #16

Max Range: 0.7126. Min Range: -0.7126

Max Act: 0.4958. Min Act: -0.0000

Data Index: 257589 (C4 (Web Text))

Max Activating Token Index: 829

Text #17

Max Range: 0.7126. Min Range: -0.7126

Max Act: 0.4611. Min Act: -0.0000

Data Index: 861390 (C4 (Web Text))

Max Activating Token Index: 324

Text #18

Max Range: 0.7126. Min Range: -0.7126

Max Act: 0.4570. Min Act: 0.0001

Data Index: 52164 (C4 (Web Text))

Max Activating Token Index: 205

Text #19

Max Range: 0.7126. Min Range: -0.7126

Max Act: 0.4667. Min Act: 0.0000

Data Index: 971414 (C4 (Web Text))

Max Activating Token Index: 412