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

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

Neuron 4181 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: 0.5160. Min Range: -0.5160

Max Act: 0.5160. Min Act: -0.0000

Data Index: 1115007 (C4 (Web Text))

Max Activating Token Index: 106

Text #1

Max Range: 0.5160. Min Range: -0.5160

Max Act: 0.4855. Min Act: -0.0000

Data Index: 1024910 (C4 (Web Text))

Max Activating Token Index: 581

Text #2

Max Range: 0.5160. Min Range: -0.5160

Max Act: 0.4839. Min Act: -0.0000

Data Index: 1305433 (C4 (Web Text))

Max Activating Token Index: 191

Text #3

Max Range: 0.5160. Min Range: -0.5160

Max Act: 0.4227. Min Act: -0.0000

Data Index: 624467 (C4 (Web Text))

Max Activating Token Index: 196

Text #4

Max Range: 0.5160. Min Range: -0.5160

Max Act: 0.4301. Min Act: -0.0000

Data Index: 735254 (C4 (Web Text))

Max Activating Token Index: 277

Text #5

Max Range: 0.5160. Min Range: -0.5160

Max Act: 0.4314. Min Act: -0.0000

Data Index: 914633 (C4 (Web Text))

Max Activating Token Index: 52

Text #6

Max Range: 0.5160. Min Range: -0.5160

Max Act: 0.4175. Min Act: -0.0000

Data Index: 616328 (C4 (Web Text))

Max Activating Token Index: 788

Text #7

Max Range: 0.5160. Min Range: -0.5160

Max Act: 0.4221. Min Act: -0.0000

Data Index: 34212 (C4 (Web Text))

Max Activating Token Index: 342

Text #8

Max Range: 0.5160. Min Range: -0.5160

Max Act: 0.4000. Min Act: -0.0000

Data Index: 464466 (C4 (Web Text))

Max Activating Token Index: 57

Text #9

Max Range: 0.5160. Min Range: -0.5160

Max Act: 0.4161. Min Act: -0.0000

Data Index: 707035 (C4 (Web Text))

Max Activating Token Index: 163

Text #10

Max Range: 0.5160. Min Range: -0.5160

Max Act: 0.3942. Min Act: -0.0000

Data Index: 321422 (C4 (Web Text))

Max Activating Token Index: 1008

Text #11

Max Range: 0.5160. Min Range: -0.5160

Max Act: 0.3806. Min Act: -0.0000

Data Index: 599787 (C4 (Web Text))

Max Activating Token Index: 606

Text #12

Max Range: 0.5160. Min Range: -0.5160

Max Act: 0.3912. Min Act: -0.0000

Data Index: 786679 (C4 (Web Text))

Max Activating Token Index: 391

Text #13

Max Range: 0.5160. Min Range: -0.5160

Max Act: 0.4010. Min Act: -0.0000

Data Index: 1026950 (C4 (Web Text))

Max Activating Token Index: 819

Text #14

Max Range: 0.5160. Min Range: -0.5160

Max Act: 0.3758. Min Act: -0.0000

Data Index: 1102127 (C4 (Web Text))

Max Activating Token Index: 519

Text #15

Max Range: 0.5160. Min Range: -0.5160

Max Act: 0.3647. Min Act: -0.0000

Data Index: 1202840 (C4 (Web Text))

Max Activating Token Index: 81

Text #16

Max Range: 0.5160. Min Range: -0.5160

Max Act: 0.3768. Min Act: -0.0000

Data Index: 718043 (C4 (Web Text))

Max Activating Token Index: 570

Text #17

Max Range: 0.5160. Min Range: -0.5160

Max Act: 0.3737. Min Act: -0.0000

Data Index: 1214379 (C4 (Web Text))

Max Activating Token Index: 571

Text #18

Max Range: 0.5160. Min Range: -0.5160

Max Act: 0.3974. Min Act: -0.0000

Data Index: 1228862 (C4 (Web Text))

Max Activating Token Index: 192

Text #19

Max Range: 0.5160. Min Range: -0.5160

Max Act: 0.3962. Min Act: -0.0000

Data Index: 966388 (C4 (Web Text))

Max Activating Token Index: 233