Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 456 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.6250. Min Range: -0.6250

Max Act: 0.5923. Min Act: -0.0001

Data Index: 1214462 (C4 (Web Text))

Max Activating Token Index: 488

Text #1

Max Range: 0.6250. Min Range: -0.6250

Max Act: 0.6250. Min Act: -0.0001

Data Index: 1225474 (C4 (Web Text))

Max Activating Token Index: 140

Text #2

Max Range: 0.6250. Min Range: -0.6250

Max Act: 0.5657. Min Act: -0.0001

Data Index: 281730 (C4 (Web Text))

Max Activating Token Index: 976

Text #3

Max Range: 0.6250. Min Range: -0.6250

Max Act: 0.5097. Min Act: -0.0000

Data Index: 801585 (C4 (Web Text))

Max Activating Token Index: 387

Text #4

Max Range: 0.6250. Min Range: -0.6250

Max Act: 0.5187. Min Act: -0.0001

Data Index: 331226 (C4 (Web Text))

Max Activating Token Index: 923

Text #5

Max Range: 0.6250. Min Range: -0.6250

Max Act: 0.4489. Min Act: -0.0000

Data Index: 1022884 (C4 (Web Text))

Max Activating Token Index: 705

Text #6

Max Range: 0.6250. Min Range: -0.6250

Max Act: 0.4541. Min Act: -0.0000

Data Index: 940183 (C4 (Web Text))

Max Activating Token Index: 728

Text #7

Max Range: 0.6250. Min Range: -0.6250

Max Act: 0.4008. Min Act: -0.0000

Data Index: 667151 (C4 (Web Text))

Max Activating Token Index: 182

Text #8

Max Range: 0.6250. Min Range: -0.6250

Max Act: 0.4220. Min Act: -0.0000

Data Index: 110100 (C4 (Web Text))

Max Activating Token Index: 547

Text #9

Max Range: 0.6250. Min Range: -0.6250

Max Act: 0.3880. Min Act: -0.0000

Data Index: 1268229 (C4 (Web Text))

Max Activating Token Index: 56

Text #10

Max Range: 0.6250. Min Range: -0.6250

Max Act: 0.4125. Min Act: -0.0000

Data Index: 684496 (C4 (Web Text))

Max Activating Token Index: 793

Text #11

Max Range: 0.6250. Min Range: -0.6250

Max Act: 0.3845. Min Act: -0.0000

Data Index: 5626 (C4 (Web Text))

Max Activating Token Index: 379

Text #12

Max Range: 0.6250. Min Range: -0.6250

Max Act: 0.4014. Min Act: -0.0000

Data Index: 962204 (C4 (Web Text))

Max Activating Token Index: 562

Text #13

Max Range: 0.6250. Min Range: -0.6250

Max Act: 0.3885. Min Act: -0.0001

Data Index: 1102034 (C4 (Web Text))

Max Activating Token Index: 552

Text #14

Max Range: 0.6250. Min Range: -0.6250

Max Act: 0.3582. Min Act: -0.0000

Data Index: 81958 (C4 (Web Text))

Max Activating Token Index: 708

Text #15

Max Range: 0.6250. Min Range: -0.6250

Max Act: 0.3682. Min Act: -0.0001

Data Index: 440880 (C4 (Web Text))

Max Activating Token Index: 732

Text #16

Max Range: 0.6250. Min Range: -0.6250

Max Act: 0.3948. Min Act: -0.0000

Data Index: 310344 (C4 (Web Text))

Max Activating Token Index: 919

Text #17

Max Range: 0.6250. Min Range: -0.6250

Max Act: 0.3870. Min Act: -0.0001

Data Index: 785177 (C4 (Web Text))

Max Activating Token Index: 1007

Text #18

Max Range: 0.6250. Min Range: -0.6250

Max Act: 0.3864. Min Act: -0.0000

Data Index: 386801 (C4 (Web Text))

Max Activating Token Index: 351

Text #19

Max Range: 0.6250. Min Range: -0.6250

Max Act: 0.3851. Min Act: -0.0000

Data Index: 654437 (C4 (Web Text))

Max Activating Token Index: 152