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

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

Neuron 5406 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6977. Min Range: -1.6977

Max Act: 1.6977. Min Act: -0.0000

Data Index: 204054 (C4 (Web Text))

Max Activating Token Index: 448

Text #1

Max Range: 1.6977. Min Range: -1.6977

Max Act: 1.4188. Min Act: -0.0000

Data Index: 467425 (C4 (Web Text))

Max Activating Token Index: 619

Text #2

Max Range: 1.6977. Min Range: -1.6977

Max Act: 1.2729. Min Act: -0.0000

Data Index: 701147 (C4 (Web Text))

Max Activating Token Index: 328

Text #3

Max Range: 1.6977. Min Range: -1.6977

Max Act: 1.2140. Min Act: -0.0000

Data Index: 103491 (C4 (Web Text))

Max Activating Token Index: 901

Text #4

Max Range: 1.6977. Min Range: -1.6977

Max Act: 1.1830. Min Act: -0.0000

Data Index: 229141 (C4 (Web Text))

Max Activating Token Index: 268

Text #5

Max Range: 1.6977. Min Range: -1.6977

Max Act: 1.1723. Min Act: -0.0000

Data Index: 240433 (C4 (Web Text))

Max Activating Token Index: 862

Text #6

Max Range: 1.6977. Min Range: -1.6977

Max Act: 1.3053. Min Act: -0.0000

Data Index: 51885 (C4 (Web Text))

Max Activating Token Index: 639

Text #7

Max Range: 1.6977. Min Range: -1.6977

Max Act: 1.2075. Min Act: -0.0000

Data Index: 912649 (C4 (Web Text))

Max Activating Token Index: 969

Text #8

Max Range: 1.6977. Min Range: -1.6977

Max Act: 1.2857. Min Act: -0.0000

Data Index: 879362 (C4 (Web Text))

Max Activating Token Index: 904

Text #9

Max Range: 1.6977. Min Range: -1.6977

Max Act: 1.1328. Min Act: -0.0000

Data Index: 1330672 (C4 (Web Text))

Max Activating Token Index: 631

Text #10

Max Range: 1.6977. Min Range: -1.6977

Max Act: 1.1169. Min Act: -0.0000

Data Index: 551861 (C4 (Web Text))

Max Activating Token Index: 440

Text #11

Max Range: 1.6977. Min Range: -1.6977

Max Act: 1.1533. Min Act: -0.0000

Data Index: 524206 (C4 (Web Text))

Max Activating Token Index: 93

Text #12

Max Range: 1.6977. Min Range: -1.6977

Max Act: 0.9943. Min Act: -0.0000

Data Index: 673889 (C4 (Web Text))

Max Activating Token Index: 884

Text #13

Max Range: 1.6977. Min Range: -1.6977

Max Act: 1.0661. Min Act: -0.0000

Data Index: 102173 (C4 (Web Text))

Max Activating Token Index: 494

Text #14

Max Range: 1.6977. Min Range: -1.6977

Max Act: 1.1100. Min Act: -0.0000

Data Index: 188426 (C4 (Web Text))

Max Activating Token Index: 354

Text #15

Max Range: 1.6977. Min Range: -1.6977

Max Act: 0.9715. Min Act: -0.0000

Data Index: 798401 (C4 (Web Text))

Max Activating Token Index: 182

Text #16

Max Range: 1.6977. Min Range: -1.6977

Max Act: 0.9829. Min Act: -0.0000

Data Index: 690063 (C4 (Web Text))

Max Activating Token Index: 835

Text #17

Max Range: 1.6977. Min Range: -1.6977

Max Act: 0.9777. Min Act: -0.0000

Data Index: 669650 (C4 (Web Text))

Max Activating Token Index: 80

Text #18

Max Range: 1.6977. Min Range: -1.6977

Max Act: 0.9122. Min Act: -0.0000

Data Index: 600030 (C4 (Web Text))

Max Activating Token Index: 298

Text #19

Max Range: 1.6977. Min Range: -1.6977

Max Act: 1.0227. Min Act: -0.0000

Data Index: 391249 (C4 (Web Text))

Max Activating Token Index: 382