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

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

Neuron 3872 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9156. Min Range: -0.9156

Max Act: 0.8981. Min Act: -0.0003

Data Index: 221874 (C4 (Web Text))

Max Activating Token Index: 946

Text #1

Max Range: 0.9156. Min Range: -0.9156

Max Act: 0.9156. Min Act: -0.0003

Data Index: 531831 (C4 (Web Text))

Max Activating Token Index: 129

Text #2

Max Range: 0.9156. Min Range: -0.9156

Max Act: 0.8828. Min Act: -0.0002

Data Index: 1284652 (C4 (Web Text))

Max Activating Token Index: 267

Text #3

Max Range: 0.9156. Min Range: -0.9156

Max Act: 0.8213. Min Act: -0.0002

Data Index: 98631 (C4 (Web Text))

Max Activating Token Index: 470

Text #4

Max Range: 0.9156. Min Range: -0.9156

Max Act: 0.7955. Min Act: -0.0003

Data Index: 95938 (C4 (Web Text))

Max Activating Token Index: 220

Text #5

Max Range: 0.9156. Min Range: -0.9156

Max Act: 0.8099. Min Act: -0.0003

Data Index: 496784 (C4 (Web Text))

Max Activating Token Index: 227

Text #6

Max Range: 0.9156. Min Range: -0.9156

Max Act: 0.7979. Min Act: -0.0002

Data Index: 547965 (C4 (Web Text))

Max Activating Token Index: 160

Text #7

Max Range: 0.9156. Min Range: -0.9156

Max Act: 0.7612. Min Act: -0.0002

Data Index: 292515 (C4 (Web Text))

Max Activating Token Index: 701

Text #8

Max Range: 0.9156. Min Range: -0.9156

Max Act: 0.7300. Min Act: -0.0002

Data Index: 164632 (C4 (Web Text))

Max Activating Token Index: 542

Text #9

Max Range: 0.9156. Min Range: -0.9156

Max Act: 0.7466. Min Act: -0.0003

Data Index: 168320 (C4 (Web Text))

Max Activating Token Index: 80

Text #10

Max Range: 0.9156. Min Range: -0.9156

Max Act: 0.7569. Min Act: -0.0003

Data Index: 644534 (C4 (Web Text))

Max Activating Token Index: 366

Text #11

Max Range: 0.9156. Min Range: -0.9156

Max Act: 0.6934. Min Act: -0.0002

Data Index: 211884 (C4 (Web Text))

Max Activating Token Index: 819

Text #12

Max Range: 0.9156. Min Range: -0.9156

Max Act: 0.6781. Min Act: -0.0003

Data Index: 531214 (C4 (Web Text))

Max Activating Token Index: 172

Text #13

Max Range: 0.9156. Min Range: -0.9156

Max Act: 0.6723. Min Act: -0.0002

Data Index: 1003947 (C4 (Web Text))

Max Activating Token Index: 807

Text #14

Max Range: 0.9156. Min Range: -0.9156

Max Act: 0.6833. Min Act: -0.0003

Data Index: 65665 (C4 (Web Text))

Max Activating Token Index: 953

Text #15

Max Range: 0.9156. Min Range: -0.9156

Max Act: 0.6719. Min Act: -0.0003

Data Index: 34969 (C4 (Web Text))

Max Activating Token Index: 304

Text #16

Max Range: 0.9156. Min Range: -0.9156

Max Act: 0.6407. Min Act: -0.0003

Data Index: 440779 (C4 (Web Text))

Max Activating Token Index: 219

Text #17

Max Range: 0.9156. Min Range: -0.9156

Max Act: 0.6747. Min Act: -0.0003

Data Index: 22514 (C4 (Web Text))

Max Activating Token Index: 181

Text #18

Max Range: 0.9156. Min Range: -0.9156

Max Act: 0.6463. Min Act: -0.0003

Data Index: 1097089 (C4 (Web Text))

Max Activating Token Index: 192

Text #19

Max Range: 0.9156. Min Range: -0.9156

Max Act: 0.6294. Min Act: -0.0002

Data Index: 602433 (C4 (Web Text))

Max Activating Token Index: 131