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

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

Neuron 435 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3094. Min Range: -0.3094

Max Act: 0.3094. Min Act: -0.0000

Data Index: 209620 (C4 (Web Text))

Max Activating Token Index: 987

Text #1

Max Range: 0.3094. Min Range: -0.3094

Max Act: 0.3025. Min Act: -0.0000

Data Index: 1253306 (C4 (Web Text))

Max Activating Token Index: 990

Text #2

Max Range: 0.3094. Min Range: -0.3094

Max Act: 0.2738. Min Act: -0.0000

Data Index: 44270 (C4 (Web Text))

Max Activating Token Index: 244

Text #3

Max Range: 0.3094. Min Range: -0.3094

Max Act: 0.2745. Min Act: -0.0000

Data Index: 698517 (C4 (Web Text))

Max Activating Token Index: 227

Text #4

Max Range: 0.3094. Min Range: -0.3094

Max Act: 0.2702. Min Act: -0.0000

Data Index: 848576 (C4 (Web Text))

Max Activating Token Index: 538

Text #5

Max Range: 0.3094. Min Range: -0.3094

Max Act: 0.2590. Min Act: -0.0000

Data Index: 624489 (C4 (Web Text))

Max Activating Token Index: 713

Text #6

Max Range: 0.3094. Min Range: -0.3094

Max Act: 0.2240. Min Act: -0.0000

Data Index: 110363 (C4 (Web Text))

Max Activating Token Index: 206

Text #7

Max Range: 0.3094. Min Range: -0.3094

Max Act: 0.2087. Min Act: -0.0000

Data Index: 857411 (C4 (Web Text))

Max Activating Token Index: 675

Text #8

Max Range: 0.3094. Min Range: -0.3094

Max Act: 0.2275. Min Act: -0.0000

Data Index: 878324 (C4 (Web Text))

Max Activating Token Index: 244

Text #9

Max Range: 0.3094. Min Range: -0.3094

Max Act: 0.2059. Min Act: -0.0000

Data Index: 207427 (C4 (Web Text))

Max Activating Token Index: 844

Text #10

Max Range: 0.3094. Min Range: -0.3094

Max Act: 0.2078. Min Act: -0.0000

Data Index: 696597 (C4 (Web Text))

Max Activating Token Index: 1017

Text #11

Max Range: 0.3094. Min Range: -0.3094

Max Act: 0.2048. Min Act: -0.0000

Data Index: 693698 (C4 (Web Text))

Max Activating Token Index: 210

Text #12

Max Range: 0.3094. Min Range: -0.3094

Max Act: 0.1933. Min Act: -0.0000

Data Index: 641054 (C4 (Web Text))

Max Activating Token Index: 661

Text #13

Max Range: 0.3094. Min Range: -0.3094

Max Act: 0.2269. Min Act: -0.0000

Data Index: 727489 (C4 (Web Text))

Max Activating Token Index: 293

Text #14

Max Range: 0.3094. Min Range: -0.3094

Max Act: 0.1942. Min Act: -0.0000

Data Index: 209028 (C4 (Web Text))

Max Activating Token Index: 921

Text #15

Max Range: 0.3094. Min Range: -0.3094

Max Act: 0.1925. Min Act: -0.0000

Data Index: 90901 (C4 (Web Text))

Max Activating Token Index: 88

Text #16

Max Range: 0.3094. Min Range: -0.3094

Max Act: 0.1727. Min Act: -0.0000

Data Index: 64829 (C4 (Web Text))

Max Activating Token Index: 100

Text #17

Max Range: 0.3094. Min Range: -0.3094

Max Act: 0.1839. Min Act: -0.0000

Data Index: 805535 (C4 (Web Text))

Max Activating Token Index: 479

Text #18

Max Range: 0.3094. Min Range: -0.3094

Max Act: 0.1834. Min Act: -0.0000

Data Index: 29429 (C4 (Web Text))

Max Activating Token Index: 993

Text #19

Max Range: 0.3094. Min Range: -0.3094

Max Act: 0.1767. Min Act: -0.0000

Data Index: 878535 (C4 (Web Text))

Max Activating Token Index: 629