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

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

Neuron 1667 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: 1.5944. Min Range: -1.5944

Max Act: 1.5055. Min Act: -0.0001

Data Index: 409936 (C4 (Web Text))

Max Activating Token Index: 545

Text #1

Max Range: 1.5944. Min Range: -1.5944

Max Act: 1.5198. Min Act: -0.0001

Data Index: 875457 (C4 (Web Text))

Max Activating Token Index: 552

Text #2

Max Range: 1.5944. Min Range: -1.5944

Max Act: 1.5944. Min Act: -0.0001

Data Index: 505067 (C4 (Web Text))

Max Activating Token Index: 873

Text #3

Max Range: 1.5944. Min Range: -1.5944

Max Act: 1.4400. Min Act: -0.0001

Data Index: 1089091 (C4 (Web Text))

Max Activating Token Index: 573

Text #4

Max Range: 1.5944. Min Range: -1.5944

Max Act: 1.4810. Min Act: -0.0001

Data Index: 308225 (C4 (Web Text))

Max Activating Token Index: 431

Text #5

Max Range: 1.5944. Min Range: -1.5944

Max Act: 1.3904. Min Act: -0.0001

Data Index: 661763 (C4 (Web Text))

Max Activating Token Index: 371

Text #6

Max Range: 1.5944. Min Range: -1.5944

Max Act: 1.3791. Min Act: -0.0001

Data Index: 558050 (C4 (Web Text))

Max Activating Token Index: 271

Text #7

Max Range: 1.5944. Min Range: -1.5944

Max Act: 1.3856. Min Act: -0.0001

Data Index: 717737 (C4 (Web Text))

Max Activating Token Index: 284

Text #8

Max Range: 1.5944. Min Range: -1.5944

Max Act: 1.4316. Min Act: -0.0001

Data Index: 1090458 (C4 (Web Text))

Max Activating Token Index: 882

Text #9

Max Range: 1.5944. Min Range: -1.5944

Max Act: 1.4358. Min Act: -0.0001

Data Index: 360726 (C4 (Web Text))

Max Activating Token Index: 375

Text #10

Max Range: 1.5944. Min Range: -1.5944

Max Act: 1.3853. Min Act: -0.0001

Data Index: 176936 (C4 (Web Text))

Max Activating Token Index: 445

Text #11

Max Range: 1.5944. Min Range: -1.5944

Max Act: 1.3169. Min Act: -0.0001

Data Index: 40368 (C4 (Web Text))

Max Activating Token Index: 343

Text #12

Max Range: 1.5944. Min Range: -1.5944

Max Act: 1.3031. Min Act: -0.0001

Data Index: 49134 (C4 (Web Text))

Max Activating Token Index: 376

Text #13

Max Range: 1.5944. Min Range: -1.5944

Max Act: 1.3764. Min Act: -0.0001

Data Index: 381501 (C4 (Web Text))

Max Activating Token Index: 731

Text #14

Max Range: 1.5944. Min Range: -1.5944

Max Act: 1.2662. Min Act: -0.0001

Data Index: 1138231 (C4 (Web Text))

Max Activating Token Index: 271

Text #15

Max Range: 1.5944. Min Range: -1.5944

Max Act: 1.2511. Min Act: -0.0001

Data Index: 4039 (C4 (Web Text))

Max Activating Token Index: 343

Text #16

Max Range: 1.5944. Min Range: -1.5944

Max Act: 1.3180. Min Act: -0.0001

Data Index: 538038 (C4 (Web Text))

Max Activating Token Index: 504

Text #17

Max Range: 1.5944. Min Range: -1.5944

Max Act: 1.2833. Min Act: -0.0001

Data Index: 899134 (C4 (Web Text))

Max Activating Token Index: 393

Text #18

Max Range: 1.5944. Min Range: -1.5944

Max Act: 1.2516. Min Act: -0.0001

Data Index: 985971 (C4 (Web Text))

Max Activating Token Index: 364

Text #19

Max Range: 1.5944. Min Range: -1.5944

Max Act: 1.3595. Min Act: -0.0001

Data Index: 595479 (C4 (Web Text))

Max Activating Token Index: 478