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

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

Neuron 1093 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: 5.5047. Min Range: -5.5047

Max Act: 5.5047. Min Act: -0.0001

Data Index: 1270077 (C4 (Web Text))

Max Activating Token Index: 631

Text #1

Max Range: 5.5047. Min Range: -5.5047

Max Act: 4.8514. Min Act: -0.0001

Data Index: 1305535 (C4 (Web Text))

Max Activating Token Index: 630

Text #2

Max Range: 5.5047. Min Range: -5.5047

Max Act: 4.3604. Min Act: -0.0001

Data Index: 1202665 (C4 (Web Text))

Max Activating Token Index: 392

Text #3

Max Range: 5.5047. Min Range: -5.5047

Max Act: 4.3177. Min Act: -0.0001

Data Index: 859299 (C4 (Web Text))

Max Activating Token Index: 1007

Text #4

Max Range: 5.5047. Min Range: -5.5047

Max Act: 4.1329. Min Act: -0.0001

Data Index: 689683 (C4 (Web Text))

Max Activating Token Index: 740

Text #5

Max Range: 5.5047. Min Range: -5.5047

Max Act: 4.4404. Min Act: -0.0001

Data Index: 421938 (C4 (Web Text))

Max Activating Token Index: 103

Text #6

Max Range: 5.5047. Min Range: -5.5047

Max Act: 4.4521. Min Act: -0.0001

Data Index: 1190977 (C4 (Web Text))

Max Activating Token Index: 769

Text #7

Max Range: 5.5047. Min Range: -5.5047

Max Act: 4.4420. Min Act: -0.0001

Data Index: 568103 (C4 (Web Text))

Max Activating Token Index: 556

Text #8

Max Range: 5.5047. Min Range: -5.5047

Max Act: 4.1835. Min Act: -0.0001

Data Index: 672235 (C4 (Web Text))

Max Activating Token Index: 883

Text #9

Max Range: 5.5047. Min Range: -5.5047

Max Act: 3.9930. Min Act: -0.0001

Data Index: 2073 (C4 (Web Text))

Max Activating Token Index: 116

Text #10

Max Range: 5.5047. Min Range: -5.5047

Max Act: 3.8827. Min Act: -0.0001

Data Index: 1197489 (C4 (Web Text))

Max Activating Token Index: 33

Text #11

Max Range: 5.5047. Min Range: -5.5047

Max Act: 3.8610. Min Act: -0.0001

Data Index: 582793 (C4 (Web Text))

Max Activating Token Index: 260

Text #12

Max Range: 5.5047. Min Range: -5.5047

Max Act: 3.7685. Min Act: -0.0001

Data Index: 966266 (C4 (Web Text))

Max Activating Token Index: 172

Text #13

Max Range: 5.5047. Min Range: -5.5047

Max Act: 4.0002. Min Act: -0.0001

Data Index: 640603 (C4 (Web Text))

Max Activating Token Index: 180

Text #14

Max Range: 5.5047. Min Range: -5.5047

Max Act: 3.8291. Min Act: -0.0001

Data Index: 862045 (C4 (Web Text))

Max Activating Token Index: 366

Text #15

Max Range: 5.5047. Min Range: -5.5047

Max Act: 3.9625. Min Act: -0.0001

Data Index: 816753 (C4 (Web Text))

Max Activating Token Index: 544

Text #16

Max Range: 5.5047. Min Range: -5.5047

Max Act: 3.4736. Min Act: -0.0001

Data Index: 771103 (C4 (Web Text))

Max Activating Token Index: 975

Text #17

Max Range: 5.5047. Min Range: -5.5047

Max Act: 3.4756. Min Act: -0.0001

Data Index: 191614 (C4 (Web Text))

Max Activating Token Index: 330

Text #18

Max Range: 5.5047. Min Range: -5.5047

Max Act: 4.1212. Min Act: -0.0001

Data Index: 104646 (C4 (Web Text))

Max Activating Token Index: 189

Text #19

Max Range: 5.5047. Min Range: -5.5047

Max Act: 3.8873. Min Act: -0.0001

Data Index: 407832 (C4 (Web Text))

Max Activating Token Index: 792