Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 90 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.3080. Min Range: -0.3080

Max Act: 0.2993. Min Act: -0.0000

Data Index: 941675 (C4 (Web Text))

Max Activating Token Index: 339

Text #1

Max Range: 0.3080. Min Range: -0.3080

Max Act: 0.3080. Min Act: -0.0000

Data Index: 513479 (C4 (Web Text))

Max Activating Token Index: 152

Text #2

Max Range: 0.3080. Min Range: -0.3080

Max Act: 0.2771. Min Act: -0.0000

Data Index: 757340 (C4 (Web Text))

Max Activating Token Index: 486

Text #3

Max Range: 0.3080. Min Range: -0.3080

Max Act: 0.2688. Min Act: -0.0000

Data Index: 924179 (C4 (Web Text))

Max Activating Token Index: 298

Text #4

Max Range: 0.3080. Min Range: -0.3080

Max Act: 0.2652. Min Act: 0.0001

Data Index: 846594 (C4 (Web Text))

Max Activating Token Index: 744

Text #5

Max Range: 0.3080. Min Range: -0.3080

Max Act: 0.2631. Min Act: 0.0001

Data Index: 1215939 (C4 (Web Text))

Max Activating Token Index: 49

Text #6

Max Range: 0.3080. Min Range: -0.3080

Max Act: 0.2514. Min Act: 0.0001

Data Index: 406115 (C4 (Web Text))

Max Activating Token Index: 229

Text #7

Max Range: 0.3080. Min Range: -0.3080

Max Act: 0.2439. Min Act: -0.0001

Data Index: 97301 (C4 (Web Text))

Max Activating Token Index: 394

Text #8

Max Range: 0.3080. Min Range: -0.3080

Max Act: 0.2418. Min Act: 0.0001

Data Index: 1311847 (C4 (Web Text))

Max Activating Token Index: 650

Text #9

Max Range: 0.3080. Min Range: -0.3080

Max Act: 0.2449. Min Act: -0.0000

Data Index: 1077728 (C4 (Web Text))

Max Activating Token Index: 1007

Text #10

Max Range: 0.3080. Min Range: -0.3080

Max Act: 0.2321. Min Act: -0.0000

Data Index: 1156372 (C4 (Web Text))

Max Activating Token Index: 109

Text #11

Max Range: 0.3080. Min Range: -0.3080

Max Act: 0.2280. Min Act: 0.0000

Data Index: 40914 (C4 (Web Text))

Max Activating Token Index: 441

Text #12

Max Range: 0.3080. Min Range: -0.3080

Max Act: 0.2283. Min Act: -0.0000

Data Index: 1054109 (C4 (Web Text))

Max Activating Token Index: 729

Text #13

Max Range: 0.3080. Min Range: -0.3080

Max Act: 0.2340. Min Act: -0.0000

Data Index: 228683 (C4 (Web Text))

Max Activating Token Index: 52

Text #14

Max Range: 0.3080. Min Range: -0.3080

Max Act: 0.2242. Min Act: 0.0001

Data Index: 1090145 (C4 (Web Text))

Max Activating Token Index: 455

Text #15

Max Range: 0.3080. Min Range: -0.3080

Max Act: 0.2295. Min Act: -0.0000

Data Index: 48670 (C4 (Web Text))

Max Activating Token Index: 112

Text #16

Max Range: 0.3080. Min Range: -0.3080

Max Act: 0.2262. Min Act: -0.0000

Data Index: 171972 (C4 (Web Text))

Max Activating Token Index: 565

Text #17

Max Range: 0.3080. Min Range: -0.3080

Max Act: 0.2275. Min Act: 0.0000

Data Index: 485457 (C4 (Web Text))

Max Activating Token Index: 43

Text #18

Max Range: 0.3080. Min Range: -0.3080

Max Act: 0.2173. Min Act: -0.0000

Data Index: 387844 (C4 (Web Text))

Max Activating Token Index: 627

Text #19

Max Range: 0.3080. Min Range: -0.3080

Max Act: 0.2224. Min Act: 0.0001

Data Index: 53302 (C4 (Web Text))

Max Activating Token Index: 104