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

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

Neuron 2806 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0884. Min Range: -2.0884

Max Act: 1.9069. Min Act: -0.0000

Data Index: 630028 (C4 (Web Text))

Max Activating Token Index: 8

Text #1

Max Range: 2.0884. Min Range: -2.0884

Max Act: 2.0884. Min Act: -0.0000

Data Index: 520656 (C4 (Web Text))

Max Activating Token Index: 843

Text #2

Max Range: 2.0884. Min Range: -2.0884

Max Act: 1.9825. Min Act: -0.0000

Data Index: 754019 (C4 (Web Text))

Max Activating Token Index: 946

Text #3

Max Range: 2.0884. Min Range: -2.0884

Max Act: 1.7976. Min Act: -0.0000

Data Index: 113260 (C4 (Web Text))

Max Activating Token Index: 883

Text #4

Max Range: 2.0884. Min Range: -2.0884

Max Act: 1.4910. Min Act: -0.0000

Data Index: 677446 (C4 (Web Text))

Max Activating Token Index: 72

Text #5

Max Range: 2.0884. Min Range: -2.0884

Max Act: 1.3977. Min Act: -0.0000

Data Index: 1390291 (Python Code)

Max Activating Token Index: 1001

Text #6

Max Range: 2.0884. Min Range: -2.0884

Max Act: 1.4693. Min Act: -0.0000

Data Index: 774632 (C4 (Web Text))

Max Activating Token Index: 594

Text #7

Max Range: 2.0884. Min Range: -2.0884

Max Act: 1.5906. Min Act: -0.0000

Data Index: 397605 (C4 (Web Text))

Max Activating Token Index: 277

Text #8

Max Range: 2.0884. Min Range: -2.0884

Max Act: 1.5369. Min Act: -0.0000

Data Index: 1294083 (C4 (Web Text))

Max Activating Token Index: 409

Text #9

Max Range: 2.0884. Min Range: -2.0884

Max Act: 1.5178. Min Act: -0.0000

Data Index: 668354 (C4 (Web Text))

Max Activating Token Index: 505

Text #10

Max Range: 2.0884. Min Range: -2.0884

Max Act: 1.5198. Min Act: -0.0000

Data Index: 1121417 (C4 (Web Text))

Max Activating Token Index: 34

Text #11

Max Range: 2.0884. Min Range: -2.0884

Max Act: 1.4353. Min Act: -0.0000

Data Index: 941485 (C4 (Web Text))

Max Activating Token Index: 882

Text #12

Max Range: 2.0884. Min Range: -2.0884

Max Act: 1.4429. Min Act: -0.0000

Data Index: 243409 (C4 (Web Text))

Max Activating Token Index: 950

Text #13

Max Range: 2.0884. Min Range: -2.0884

Max Act: 1.6082. Min Act: -0.0000

Data Index: 1367386 (Python Code)

Max Activating Token Index: 773

Text #14

Max Range: 2.0884. Min Range: -2.0884

Max Act: 1.3654. Min Act: -0.0000

Data Index: 485421 (C4 (Web Text))

Max Activating Token Index: 865

Text #15

Max Range: 2.0884. Min Range: -2.0884

Max Act: 1.2705. Min Act: -0.0000

Data Index: 877982 (C4 (Web Text))

Max Activating Token Index: 669

Text #16

Max Range: 2.0884. Min Range: -2.0884

Max Act: 1.3170. Min Act: -0.0000

Data Index: 1094764 (C4 (Web Text))

Max Activating Token Index: 794

Text #17

Max Range: 2.0884. Min Range: -2.0884

Max Act: 1.3805. Min Act: -0.0000

Data Index: 1113307 (C4 (Web Text))

Max Activating Token Index: 387

Text #18

Max Range: 2.0884. Min Range: -2.0884

Max Act: 1.3004. Min Act: -0.0000

Data Index: 324380 (C4 (Web Text))

Max Activating Token Index: 9

Text #19

Max Range: 2.0884. Min Range: -2.0884

Max Act: 1.3613. Min Act: -0.0000

Data Index: 1062958 (C4 (Web Text))

Max Activating Token Index: 787