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

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

Neuron 2479 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5529. Min Range: -1.5529

Max Act: 1.5529. Min Act: -0.0000

Data Index: 576880 (C4 (Web Text))

Max Activating Token Index: 368

Text #1

Max Range: 1.5529. Min Range: -1.5529

Max Act: 1.4926. Min Act: -0.0000

Data Index: 208672 (C4 (Web Text))

Max Activating Token Index: 42

Text #2

Max Range: 1.5529. Min Range: -1.5529

Max Act: 1.3431. Min Act: -0.0000

Data Index: 157696 (C4 (Web Text))

Max Activating Token Index: 48

Text #3

Max Range: 1.5529. Min Range: -1.5529

Max Act: 1.4209. Min Act: -0.0000

Data Index: 383685 (C4 (Web Text))

Max Activating Token Index: 709

Text #4

Max Range: 1.5529. Min Range: -1.5529

Max Act: 1.1018. Min Act: -0.0000

Data Index: 944288 (C4 (Web Text))

Max Activating Token Index: 929

Text #5

Max Range: 1.5529. Min Range: -1.5529

Max Act: 1.0925. Min Act: -0.0000

Data Index: 461789 (C4 (Web Text))

Max Activating Token Index: 36

Text #6

Max Range: 1.5529. Min Range: -1.5529

Max Act: 1.0861. Min Act: -0.0000

Data Index: 1088076 (C4 (Web Text))

Max Activating Token Index: 848

Text #7

Max Range: 1.5529. Min Range: -1.5529

Max Act: 1.0112. Min Act: -0.0000

Data Index: 301559 (C4 (Web Text))

Max Activating Token Index: 504

Text #8

Max Range: 1.5529. Min Range: -1.5529

Max Act: 1.0944. Min Act: -0.0000

Data Index: 368227 (C4 (Web Text))

Max Activating Token Index: 430

Text #9

Max Range: 1.5529. Min Range: -1.5529

Max Act: 1.0082. Min Act: -0.0000

Data Index: 1266749 (C4 (Web Text))

Max Activating Token Index: 438

Text #10

Max Range: 1.5529. Min Range: -1.5529

Max Act: 0.9657. Min Act: -0.0000

Data Index: 175978 (C4 (Web Text))

Max Activating Token Index: 10

Text #11

Max Range: 1.5529. Min Range: -1.5529

Max Act: 1.0218. Min Act: -0.0000

Data Index: 1125422 (C4 (Web Text))

Max Activating Token Index: 304

Text #12

Max Range: 1.5529. Min Range: -1.5529

Max Act: 1.0505. Min Act: -0.0000

Data Index: 79620 (C4 (Web Text))

Max Activating Token Index: 648

Text #13

Max Range: 1.5529. Min Range: -1.5529

Max Act: 0.9844. Min Act: -0.0000

Data Index: 1103290 (C4 (Web Text))

Max Activating Token Index: 221

Text #14

Max Range: 1.5529. Min Range: -1.5529

Max Act: 1.0069. Min Act: -0.0000

Data Index: 1272121 (C4 (Web Text))

Max Activating Token Index: 199

Text #15

Max Range: 1.5529. Min Range: -1.5529

Max Act: 0.9968. Min Act: -0.0000

Data Index: 1194239 (C4 (Web Text))

Max Activating Token Index: 811

Text #16

Max Range: 1.5529. Min Range: -1.5529

Max Act: 0.7745. Min Act: -0.0000

Data Index: 1042760 (C4 (Web Text))

Max Activating Token Index: 722

Text #17

Max Range: 1.5529. Min Range: -1.5529

Max Act: 1.0107. Min Act: -0.0000

Data Index: 179987 (C4 (Web Text))

Max Activating Token Index: 590

Text #18

Max Range: 1.5529. Min Range: -1.5529

Max Act: 1.0235. Min Act: -0.0000

Data Index: 659341 (C4 (Web Text))

Max Activating Token Index: 210

Text #19

Max Range: 1.5529. Min Range: -1.5529

Max Act: 0.8521. Min Act: -0.0000

Data Index: 893899 (C4 (Web Text))

Max Activating Token Index: 917