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

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

Neuron 3414 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2545. Min Range: -0.2545

Max Act: 0.2492. Min Act: -0.0000

Data Index: 11534 (C4 (Web Text))

Max Activating Token Index: 670

Text #1

Max Range: 0.2545. Min Range: -0.2545

Max Act: 0.2440. Min Act: -0.0000

Data Index: 138566 (C4 (Web Text))

Max Activating Token Index: 924

Text #2

Max Range: 0.2545. Min Range: -0.2545

Max Act: 0.2545. Min Act: -0.0000

Data Index: 882642 (C4 (Web Text))

Max Activating Token Index: 531

Text #3

Max Range: 0.2545. Min Range: -0.2545

Max Act: 0.2134. Min Act: -0.0000

Data Index: 283061 (C4 (Web Text))

Max Activating Token Index: 787

Text #4

Max Range: 0.2545. Min Range: -0.2545

Max Act: 0.2450. Min Act: -0.0000

Data Index: 30170 (C4 (Web Text))

Max Activating Token Index: 276

Text #5

Max Range: 0.2545. Min Range: -0.2545

Max Act: 0.2449. Min Act: -0.0000

Data Index: 759334 (C4 (Web Text))

Max Activating Token Index: 378

Text #6

Max Range: 0.2545. Min Range: -0.2545

Max Act: 0.2353. Min Act: -0.0000

Data Index: 1148940 (C4 (Web Text))

Max Activating Token Index: 492

Text #7

Max Range: 0.2545. Min Range: -0.2545

Max Act: 0.2199. Min Act: -0.0000

Data Index: 194627 (C4 (Web Text))

Max Activating Token Index: 133

Text #8

Max Range: 0.2545. Min Range: -0.2545

Max Act: 0.2089. Min Act: -0.0000

Data Index: 103045 (C4 (Web Text))

Max Activating Token Index: 773

Text #9

Max Range: 0.2545. Min Range: -0.2545

Max Act: 0.2140. Min Act: -0.0000

Data Index: 849483 (C4 (Web Text))

Max Activating Token Index: 995

Text #10

Max Range: 0.2545. Min Range: -0.2545

Max Act: 0.2167. Min Act: -0.0000

Data Index: 1301013 (C4 (Web Text))

Max Activating Token Index: 103

Text #11

Max Range: 0.2545. Min Range: -0.2545

Max Act: 0.2101. Min Act: -0.0000

Data Index: 883476 (C4 (Web Text))

Max Activating Token Index: 644

Text #12

Max Range: 0.2545. Min Range: -0.2545

Max Act: 0.2102. Min Act: -0.0000

Data Index: 454739 (C4 (Web Text))

Max Activating Token Index: 227

Text #13

Max Range: 0.2545. Min Range: -0.2545

Max Act: 0.2062. Min Act: -0.0000

Data Index: 539120 (C4 (Web Text))

Max Activating Token Index: 284

Text #14

Max Range: 0.2545. Min Range: -0.2545

Max Act: 0.2056. Min Act: -0.0000

Data Index: 456313 (C4 (Web Text))

Max Activating Token Index: 192

Text #15

Max Range: 0.2545. Min Range: -0.2545

Max Act: 0.2050. Min Act: -0.0000

Data Index: 300842 (C4 (Web Text))

Max Activating Token Index: 340

Text #16

Max Range: 0.2545. Min Range: -0.2545

Max Act: 0.1641. Min Act: -0.0000

Data Index: 1068483 (C4 (Web Text))

Max Activating Token Index: 233

Text #17

Max Range: 0.2545. Min Range: -0.2545

Max Act: 0.2090. Min Act: -0.0000

Data Index: 846486 (C4 (Web Text))

Max Activating Token Index: 43

Text #18

Max Range: 0.2545. Min Range: -0.2545

Max Act: 0.2014. Min Act: -0.0000

Data Index: 711466 (C4 (Web Text))

Max Activating Token Index: 367

Text #19

Max Range: 0.2545. Min Range: -0.2545

Max Act: 0.2017. Min Act: -0.0000

Data Index: 753678 (C4 (Web Text))

Max Activating Token Index: 125