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

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

Neuron 451 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: 1.5137. Min Range: -1.5137

Max Act: 1.5137. Min Act: -0.0000

Data Index: 651934 (C4 (Web Text))

Max Activating Token Index: 731

Text #1

Max Range: 1.5137. Min Range: -1.5137

Max Act: 1.5046. Min Act: -0.0000

Data Index: 472125 (C4 (Web Text))

Max Activating Token Index: 744

Text #2

Max Range: 1.5137. Min Range: -1.5137

Max Act: 1.4905. Min Act: -0.0000

Data Index: 483632 (C4 (Web Text))

Max Activating Token Index: 21

Text #3

Max Range: 1.5137. Min Range: -1.5137

Max Act: 1.3321. Min Act: -0.0000

Data Index: 1131663 (C4 (Web Text))

Max Activating Token Index: 747

Text #4

Max Range: 1.5137. Min Range: -1.5137

Max Act: 1.4517. Min Act: -0.0000

Data Index: 416268 (C4 (Web Text))

Max Activating Token Index: 245

Text #5

Max Range: 1.5137. Min Range: -1.5137

Max Act: 1.2545. Min Act: -0.0000

Data Index: 1135376 (C4 (Web Text))

Max Activating Token Index: 81

Text #6

Max Range: 1.5137. Min Range: -1.5137

Max Act: 1.3302. Min Act: -0.0000

Data Index: 1124117 (C4 (Web Text))

Max Activating Token Index: 826

Text #7

Max Range: 1.5137. Min Range: -1.5137

Max Act: 1.3176. Min Act: -0.0000

Data Index: 538235 (C4 (Web Text))

Max Activating Token Index: 942

Text #8

Max Range: 1.5137. Min Range: -1.5137

Max Act: 1.1746. Min Act: -0.0000

Data Index: 1534530 (Python Code)

Max Activating Token Index: 620

Text #9

Max Range: 1.5137. Min Range: -1.5137

Max Act: 1.2188. Min Act: -0.0000

Data Index: 1057338 (C4 (Web Text))

Max Activating Token Index: 823

Text #10

Max Range: 1.5137. Min Range: -1.5137

Max Act: 1.2771. Min Act: -0.0000

Data Index: 1290055 (C4 (Web Text))

Max Activating Token Index: 926

Text #11

Max Range: 1.5137. Min Range: -1.5137

Max Act: 1.2530. Min Act: -0.0000

Data Index: 1303037 (C4 (Web Text))

Max Activating Token Index: 94

Text #12

Max Range: 1.5137. Min Range: -1.5137

Max Act: 1.1456. Min Act: -0.0000

Data Index: 199333 (C4 (Web Text))

Max Activating Token Index: 522

Text #13

Max Range: 1.5137. Min Range: -1.5137

Max Act: 1.2173. Min Act: -0.0000

Data Index: 429035 (C4 (Web Text))

Max Activating Token Index: 394

Text #14

Max Range: 1.5137. Min Range: -1.5137

Max Act: 1.1324. Min Act: -0.0000

Data Index: 957972 (C4 (Web Text))

Max Activating Token Index: 194

Text #15

Max Range: 1.5137. Min Range: -1.5137

Max Act: 1.0001. Min Act: -0.0000

Data Index: 226046 (C4 (Web Text))

Max Activating Token Index: 217

Text #16

Max Range: 1.5137. Min Range: -1.5137

Max Act: 1.0336. Min Act: 0.0000

Data Index: 1180389 (C4 (Web Text))

Max Activating Token Index: 457

Text #17

Max Range: 1.5137. Min Range: -1.5137

Max Act: 1.0280. Min Act: -0.0000

Data Index: 1463464 (Python Code)

Max Activating Token Index: 495

Text #18

Max Range: 1.5137. Min Range: -1.5137

Max Act: 1.0015. Min Act: -0.0000

Data Index: 375575 (C4 (Web Text))

Max Activating Token Index: 44

Text #19

Max Range: 1.5137. Min Range: -1.5137

Max Act: 0.9260. Min Act: -0.0000

Data Index: 288145 (C4 (Web Text))

Max Activating Token Index: 805