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

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

Neuron 1876 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4206. Min Range: -0.4206

Max Act: 0.4206. Min Act: -0.0001

Data Index: 1127399 (C4 (Web Text))

Max Activating Token Index: 657

Text #1

Max Range: 0.4206. Min Range: -0.4206

Max Act: 0.4148. Min Act: -0.0001

Data Index: 438747 (C4 (Web Text))

Max Activating Token Index: 567

Text #2

Max Range: 0.4206. Min Range: -0.4206

Max Act: 0.3630. Min Act: -0.0001

Data Index: 765587 (C4 (Web Text))

Max Activating Token Index: 368

Text #3

Max Range: 0.4206. Min Range: -0.4206

Max Act: 0.3053. Min Act: -0.0001

Data Index: 57194 (C4 (Web Text))

Max Activating Token Index: 210

Text #4

Max Range: 0.4206. Min Range: -0.4206

Max Act: 0.3035. Min Act: -0.0001

Data Index: 28297 (C4 (Web Text))

Max Activating Token Index: 102

Text #5

Max Range: 0.4206. Min Range: -0.4206

Max Act: 0.2897. Min Act: -0.0001

Data Index: 604549 (C4 (Web Text))

Max Activating Token Index: 885

Text #6

Max Range: 0.4206. Min Range: -0.4206

Max Act: 0.3037. Min Act: -0.0001

Data Index: 954823 (C4 (Web Text))

Max Activating Token Index: 647

Text #7

Max Range: 0.4206. Min Range: -0.4206

Max Act: 0.3020. Min Act: -0.0001

Data Index: 172709 (C4 (Web Text))

Max Activating Token Index: 86

Text #8

Max Range: 0.4206. Min Range: -0.4206

Max Act: 0.3231. Min Act: -0.0001

Data Index: 1398786 (Python Code)

Max Activating Token Index: 794

Text #9

Max Range: 0.4206. Min Range: -0.4206

Max Act: 0.2757. Min Act: -0.0001

Data Index: 1498867 (Python Code)

Max Activating Token Index: 359

Text #10

Max Range: 0.4206. Min Range: -0.4206

Max Act: 0.2641. Min Act: -0.0001

Data Index: 547170 (C4 (Web Text))

Max Activating Token Index: 555

Text #11

Max Range: 0.4206. Min Range: -0.4206

Max Act: 0.2609. Min Act: -0.0001

Data Index: 1031662 (C4 (Web Text))

Max Activating Token Index: 638

Text #12

Max Range: 0.4206. Min Range: -0.4206

Max Act: 0.2710. Min Act: -0.0001

Data Index: 594399 (C4 (Web Text))

Max Activating Token Index: 734

Text #13

Max Range: 0.4206. Min Range: -0.4206

Max Act: 0.2604. Min Act: -0.0001

Data Index: 73384 (C4 (Web Text))

Max Activating Token Index: 787

Text #14

Max Range: 0.4206. Min Range: -0.4206

Max Act: 0.2462. Min Act: -0.0001

Data Index: 212961 (C4 (Web Text))

Max Activating Token Index: 972

Text #15

Max Range: 0.4206. Min Range: -0.4206

Max Act: 0.2246. Min Act: -0.0001

Data Index: 276992 (C4 (Web Text))

Max Activating Token Index: 645

Text #16

Max Range: 0.4206. Min Range: -0.4206

Max Act: 0.2198. Min Act: -0.0001

Data Index: 328756 (C4 (Web Text))

Max Activating Token Index: 1006

Text #17

Max Range: 0.4206. Min Range: -0.4206

Max Act: 0.2322. Min Act: -0.0001

Data Index: 895837 (C4 (Web Text))

Max Activating Token Index: 744

Text #18

Max Range: 0.4206. Min Range: -0.4206

Max Act: 0.2277. Min Act: -0.0001

Data Index: 338243 (C4 (Web Text))

Max Activating Token Index: 923

Text #19

Max Range: 0.4206. Min Range: -0.4206

Max Act: 0.2108. Min Act: -0.0001

Data Index: 1418080 (Python Code)

Max Activating Token Index: 908