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

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

Neuron 2124 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5259. Min Range: -0.5259

Max Act: 0.5088. Min Act: -0.0000

Data Index: 1227700 (C4 (Web Text))

Max Activating Token Index: 734

Text #1

Max Range: 0.5259. Min Range: -0.5259

Max Act: 0.5137. Min Act: -0.0000

Data Index: 322244 (C4 (Web Text))

Max Activating Token Index: 993

Text #2

Max Range: 0.5259. Min Range: -0.5259

Max Act: 0.5259. Min Act: -0.0000

Data Index: 995152 (C4 (Web Text))

Max Activating Token Index: 89

Text #3

Max Range: 0.5259. Min Range: -0.5259

Max Act: 0.4933. Min Act: -0.0000

Data Index: 349778 (C4 (Web Text))

Max Activating Token Index: 512

Text #4

Max Range: 0.5259. Min Range: -0.5259

Max Act: 0.5055. Min Act: -0.0000

Data Index: 944280 (C4 (Web Text))

Max Activating Token Index: 832

Text #5

Max Range: 0.5259. Min Range: -0.5259

Max Act: 0.5224. Min Act: -0.0000

Data Index: 1187732 (C4 (Web Text))

Max Activating Token Index: 303

Text #6

Max Range: 0.5259. Min Range: -0.5259

Max Act: 0.5071. Min Act: -0.0000

Data Index: 916095 (C4 (Web Text))

Max Activating Token Index: 107

Text #7

Max Range: 0.5259. Min Range: -0.5259

Max Act: 0.4404. Min Act: -0.0000

Data Index: 276267 (C4 (Web Text))

Max Activating Token Index: 790

Text #8

Max Range: 0.5259. Min Range: -0.5259

Max Act: 0.4643. Min Act: -0.0000

Data Index: 1151496 (C4 (Web Text))

Max Activating Token Index: 707

Text #9

Max Range: 0.5259. Min Range: -0.5259

Max Act: 0.5000. Min Act: -0.0000

Data Index: 892571 (C4 (Web Text))

Max Activating Token Index: 489

Text #10

Max Range: 0.5259. Min Range: -0.5259

Max Act: 0.5154. Min Act: -0.0000

Data Index: 763288 (C4 (Web Text))

Max Activating Token Index: 685

Text #11

Max Range: 0.5259. Min Range: -0.5259

Max Act: 0.4364. Min Act: -0.0000

Data Index: 81047 (C4 (Web Text))

Max Activating Token Index: 713

Text #12

Max Range: 0.5259. Min Range: -0.5259

Max Act: 0.4855. Min Act: -0.0000

Data Index: 755958 (C4 (Web Text))

Max Activating Token Index: 724

Text #13

Max Range: 0.5259. Min Range: -0.5259

Max Act: 0.3736. Min Act: -0.0000

Data Index: 255770 (C4 (Web Text))

Max Activating Token Index: 303

Text #14

Max Range: 0.5259. Min Range: -0.5259

Max Act: 0.4253. Min Act: -0.0000

Data Index: 5314 (C4 (Web Text))

Max Activating Token Index: 471

Text #15

Max Range: 0.5259. Min Range: -0.5259

Max Act: 0.4538. Min Act: -0.0000

Data Index: 1288967 (C4 (Web Text))

Max Activating Token Index: 426

Text #16

Max Range: 0.5259. Min Range: -0.5259

Max Act: 0.4472. Min Act: -0.0000

Data Index: 1013594 (C4 (Web Text))

Max Activating Token Index: 657

Text #17

Max Range: 0.5259. Min Range: -0.5259

Max Act: 0.3746. Min Act: -0.0000

Data Index: 56072 (C4 (Web Text))

Max Activating Token Index: 614

Text #18

Max Range: 0.5259. Min Range: -0.5259

Max Act: 0.3966. Min Act: -0.0000

Data Index: 678416 (C4 (Web Text))

Max Activating Token Index: 188

Text #19

Max Range: 0.5259. Min Range: -0.5259

Max Act: 0.4145. Min Act: -0.0000

Data Index: 427113 (C4 (Web Text))

Max Activating Token Index: 349