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

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

Neuron 3411 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.3094. Min Range: -1.3094

Max Act: 1.3094. Min Act: -0.0001

Data Index: 230530 (C4 (Web Text))

Max Activating Token Index: 803

Text #1

Max Range: 1.3094. Min Range: -1.3094

Max Act: 1.1500. Min Act: -0.0001

Data Index: 608815 (C4 (Web Text))

Max Activating Token Index: 712

Text #2

Max Range: 1.3094. Min Range: -1.3094

Max Act: 1.1721. Min Act: -0.0001

Data Index: 864816 (C4 (Web Text))

Max Activating Token Index: 507

Text #3

Max Range: 1.3094. Min Range: -1.3094

Max Act: 1.1665. Min Act: -0.0001

Data Index: 888223 (C4 (Web Text))

Max Activating Token Index: 409

Text #4

Max Range: 1.3094. Min Range: -1.3094

Max Act: 1.1728. Min Act: -0.0001

Data Index: 244008 (C4 (Web Text))

Max Activating Token Index: 30

Text #5

Max Range: 1.3094. Min Range: -1.3094

Max Act: 1.0866. Min Act: -0.0001

Data Index: 1887 (C4 (Web Text))

Max Activating Token Index: 489

Text #6

Max Range: 1.3094. Min Range: -1.3094

Max Act: 1.1087. Min Act: -0.0001

Data Index: 1306331 (C4 (Web Text))

Max Activating Token Index: 921

Text #7

Max Range: 1.3094. Min Range: -1.3094

Max Act: 1.0538. Min Act: -0.0001

Data Index: 297940 (C4 (Web Text))

Max Activating Token Index: 948

Text #8

Max Range: 1.3094. Min Range: -1.3094

Max Act: 1.0003. Min Act: -0.0001

Data Index: 1180278 (C4 (Web Text))

Max Activating Token Index: 153

Text #9

Max Range: 1.3094. Min Range: -1.3094

Max Act: 1.0518. Min Act: -0.0001

Data Index: 521942 (C4 (Web Text))

Max Activating Token Index: 819

Text #10

Max Range: 1.3094. Min Range: -1.3094

Max Act: 1.0422. Min Act: -0.0001

Data Index: 1126054 (C4 (Web Text))

Max Activating Token Index: 92

Text #11

Max Range: 1.3094. Min Range: -1.3094

Max Act: 1.0336. Min Act: -0.0001

Data Index: 747601 (C4 (Web Text))

Max Activating Token Index: 129

Text #12

Max Range: 1.3094. Min Range: -1.3094

Max Act: 1.0174. Min Act: -0.0001

Data Index: 1327056 (C4 (Web Text))

Max Activating Token Index: 329

Text #13

Max Range: 1.3094. Min Range: -1.3094

Max Act: 0.9009. Min Act: -0.0001

Data Index: 140235 (C4 (Web Text))

Max Activating Token Index: 743

Text #14

Max Range: 1.3094. Min Range: -1.3094

Max Act: 1.0146. Min Act: -0.0001

Data Index: 441830 (C4 (Web Text))

Max Activating Token Index: 442

Text #15

Max Range: 1.3094. Min Range: -1.3094

Max Act: 0.9287. Min Act: -0.0001

Data Index: 639748 (C4 (Web Text))

Max Activating Token Index: 472

Text #16

Max Range: 1.3094. Min Range: -1.3094

Max Act: 1.0170. Min Act: -0.0001

Data Index: 1301857 (C4 (Web Text))

Max Activating Token Index: 946

Text #17

Max Range: 1.3094. Min Range: -1.3094

Max Act: 0.9707. Min Act: -0.0001

Data Index: 1199304 (C4 (Web Text))

Max Activating Token Index: 356

Text #18

Max Range: 1.3094. Min Range: -1.3094

Max Act: 0.9540. Min Act: -0.0001

Data Index: 17784 (C4 (Web Text))

Max Activating Token Index: 692

Text #19

Max Range: 1.3094. Min Range: -1.3094

Max Act: 1.0633. Min Act: -0.0001

Data Index: 1108094 (C4 (Web Text))

Max Activating Token Index: 897