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

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

Neuron 973 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.6081. Min Range: -4.6081

Max Act: 4.6081. Min Act: -0.0000

Data Index: 1098378 (C4 (Web Text))

Max Activating Token Index: 529

Text #1

Max Range: 4.6081. Min Range: -4.6081

Max Act: 2.8245. Min Act: -0.0000

Data Index: 1004498 (C4 (Web Text))

Max Activating Token Index: 108

Text #2

Max Range: 4.6081. Min Range: -4.6081

Max Act: 2.7228. Min Act: -0.0000

Data Index: 339367 (C4 (Web Text))

Max Activating Token Index: 55

Text #3

Max Range: 4.6081. Min Range: -4.6081

Max Act: 2.7142. Min Act: -0.0000

Data Index: 272389 (C4 (Web Text))

Max Activating Token Index: 185

Text #4

Max Range: 4.6081. Min Range: -4.6081

Max Act: 2.7029. Min Act: -0.0000

Data Index: 887004 (C4 (Web Text))

Max Activating Token Index: 479

Text #5

Max Range: 4.6081. Min Range: -4.6081

Max Act: 2.6265. Min Act: -0.0000

Data Index: 175915 (C4 (Web Text))

Max Activating Token Index: 115

Text #6

Max Range: 4.6081. Min Range: -4.6081

Max Act: 2.6128. Min Act: -0.0000

Data Index: 1004422 (C4 (Web Text))

Max Activating Token Index: 296

Text #7

Max Range: 4.6081. Min Range: -4.6081

Max Act: 2.3259. Min Act: -0.0000

Data Index: 554572 (C4 (Web Text))

Max Activating Token Index: 233

Text #8

Max Range: 4.6081. Min Range: -4.6081

Max Act: 2.5384. Min Act: -0.0000

Data Index: 132172 (C4 (Web Text))

Max Activating Token Index: 805

Text #9

Max Range: 4.6081. Min Range: -4.6081

Max Act: 2.2591. Min Act: -0.0000

Data Index: 708280 (C4 (Web Text))

Max Activating Token Index: 192

Text #10

Max Range: 4.6081. Min Range: -4.6081

Max Act: 2.5005. Min Act: -0.0000

Data Index: 1085455 (C4 (Web Text))

Max Activating Token Index: 903

Text #11

Max Range: 4.6081. Min Range: -4.6081

Max Act: 2.3280. Min Act: -0.0000

Data Index: 377235 (C4 (Web Text))

Max Activating Token Index: 663

Text #12

Max Range: 4.6081. Min Range: -4.6081

Max Act: 2.4469. Min Act: -0.0000

Data Index: 1123615 (C4 (Web Text))

Max Activating Token Index: 397

Text #13

Max Range: 4.6081. Min Range: -4.6081

Max Act: 2.5131. Min Act: -0.0000

Data Index: 1278933 (C4 (Web Text))

Max Activating Token Index: 756

Text #14

Max Range: 4.6081. Min Range: -4.6081

Max Act: 2.2810. Min Act: -0.0000

Data Index: 1239112 (C4 (Web Text))

Max Activating Token Index: 131

Text #15

Max Range: 4.6081. Min Range: -4.6081

Max Act: 2.4573. Min Act: -0.0000

Data Index: 392048 (C4 (Web Text))

Max Activating Token Index: 190

Text #16

Max Range: 4.6081. Min Range: -4.6081

Max Act: 2.3211. Min Act: -0.0000

Data Index: 486352 (C4 (Web Text))

Max Activating Token Index: 421

Text #17

Max Range: 4.6081. Min Range: -4.6081

Max Act: 2.3903. Min Act: -0.0000

Data Index: 538952 (C4 (Web Text))

Max Activating Token Index: 451

Text #18

Max Range: 4.6081. Min Range: -4.6081

Max Act: 2.2357. Min Act: -0.0000

Data Index: 243725 (C4 (Web Text))

Max Activating Token Index: 693

Text #19

Max Range: 4.6081. Min Range: -4.6081

Max Act: 2.1411. Min Act: -0.0000

Data Index: 1311832 (C4 (Web Text))

Max Activating Token Index: 934