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

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

Neuron 2310 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2819. Min Range: -2.2819

Max Act: 2.0834. Min Act: -0.0000

Data Index: 173346 (C4 (Web Text))

Max Activating Token Index: 159

Text #1

Max Range: 2.2819. Min Range: -2.2819

Max Act: 2.2819. Min Act: -0.0000

Data Index: 266680 (C4 (Web Text))

Max Activating Token Index: 377

Text #2

Max Range: 2.2819. Min Range: -2.2819

Max Act: 2.1265. Min Act: -0.0000

Data Index: 1305605 (C4 (Web Text))

Max Activating Token Index: 715

Text #3

Max Range: 2.2819. Min Range: -2.2819

Max Act: 1.9641. Min Act: -0.0000

Data Index: 281330 (C4 (Web Text))

Max Activating Token Index: 70

Text #4

Max Range: 2.2819. Min Range: -2.2819

Max Act: 1.7562. Min Act: -0.0000

Data Index: 619307 (C4 (Web Text))

Max Activating Token Index: 917

Text #5

Max Range: 2.2819. Min Range: -2.2819

Max Act: 1.9155. Min Act: -0.0000

Data Index: 491290 (C4 (Web Text))

Max Activating Token Index: 772

Text #6

Max Range: 2.2819. Min Range: -2.2819

Max Act: 1.9250. Min Act: -0.0000

Data Index: 585101 (C4 (Web Text))

Max Activating Token Index: 278

Text #7

Max Range: 2.2819. Min Range: -2.2819

Max Act: 1.7979. Min Act: -0.0000

Data Index: 715100 (C4 (Web Text))

Max Activating Token Index: 96

Text #8

Max Range: 2.2819. Min Range: -2.2819

Max Act: 2.0001. Min Act: -0.0000

Data Index: 728638 (C4 (Web Text))

Max Activating Token Index: 700

Text #9

Max Range: 2.2819. Min Range: -2.2819

Max Act: 1.9421. Min Act: -0.0000

Data Index: 412832 (C4 (Web Text))

Max Activating Token Index: 151

Text #10

Max Range: 2.2819. Min Range: -2.2819

Max Act: 1.8011. Min Act: -0.0000

Data Index: 1083570 (C4 (Web Text))

Max Activating Token Index: 217

Text #11

Max Range: 2.2819. Min Range: -2.2819

Max Act: 1.7985. Min Act: -0.0000

Data Index: 164678 (C4 (Web Text))

Max Activating Token Index: 465

Text #12

Max Range: 2.2819. Min Range: -2.2819

Max Act: 1.7908. Min Act: -0.0000

Data Index: 464521 (C4 (Web Text))

Max Activating Token Index: 117

Text #13

Max Range: 2.2819. Min Range: -2.2819

Max Act: 1.9524. Min Act: -0.0000

Data Index: 1154471 (C4 (Web Text))

Max Activating Token Index: 493

Text #14

Max Range: 2.2819. Min Range: -2.2819

Max Act: 1.8569. Min Act: -0.0000

Data Index: 29864 (C4 (Web Text))

Max Activating Token Index: 877

Text #15

Max Range: 2.2819. Min Range: -2.2819

Max Act: 1.8447. Min Act: -0.0000

Data Index: 178871 (C4 (Web Text))

Max Activating Token Index: 546

Text #16

Max Range: 2.2819. Min Range: -2.2819

Max Act: 1.6489. Min Act: -0.0000

Data Index: 1299046 (C4 (Web Text))

Max Activating Token Index: 930

Text #17

Max Range: 2.2819. Min Range: -2.2819

Max Act: 1.7513. Min Act: -0.0000

Data Index: 1231343 (C4 (Web Text))

Max Activating Token Index: 990

Text #18

Max Range: 2.2819. Min Range: -2.2819

Max Act: 1.7405. Min Act: -0.0000

Data Index: 408150 (C4 (Web Text))

Max Activating Token Index: 1007

Text #19

Max Range: 2.2819. Min Range: -2.2819

Max Act: 1.8076. Min Act: -0.0000

Data Index: 995968 (C4 (Web Text))

Max Activating Token Index: 737