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

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

Neuron 4885 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: 6.7735. Min Range: -6.7735

Max Act: 6.7735. Min Act: -0.0000

Data Index: 84788 (C4 (Web Text))

Max Activating Token Index: 50

Text #1

Max Range: 6.7735. Min Range: -6.7735

Max Act: 6.5842. Min Act: -0.0000

Data Index: 733339 (C4 (Web Text))

Max Activating Token Index: 49

Text #2

Max Range: 6.7735. Min Range: -6.7735

Max Act: 5.8720. Min Act: -0.0000

Data Index: 552571 (C4 (Web Text))

Max Activating Token Index: 129

Text #3

Max Range: 6.7735. Min Range: -6.7735

Max Act: 5.8675. Min Act: -0.0000

Data Index: 86410 (C4 (Web Text))

Max Activating Token Index: 154

Text #4

Max Range: 6.7735. Min Range: -6.7735

Max Act: 5.4971. Min Act: -0.0000

Data Index: 278405 (C4 (Web Text))

Max Activating Token Index: 320

Text #5

Max Range: 6.7735. Min Range: -6.7735

Max Act: 5.4867. Min Act: -0.0000

Data Index: 406025 (C4 (Web Text))

Max Activating Token Index: 314

Text #6

Max Range: 6.7735. Min Range: -6.7735

Max Act: 5.4711. Min Act: -0.0000

Data Index: 1005353 (C4 (Web Text))

Max Activating Token Index: 158

Text #7

Max Range: 6.7735. Min Range: -6.7735

Max Act: 5.4434. Min Act: -0.0000

Data Index: 963528 (C4 (Web Text))

Max Activating Token Index: 317

Text #8

Max Range: 6.7735. Min Range: -6.7735

Max Act: 5.4410. Min Act: -0.0000

Data Index: 1082207 (C4 (Web Text))

Max Activating Token Index: 99

Text #9

Max Range: 6.7735. Min Range: -6.7735

Max Act: 5.1537. Min Act: -0.0000

Data Index: 75904 (C4 (Web Text))

Max Activating Token Index: 1019

Text #10

Max Range: 6.7735. Min Range: -6.7735

Max Act: 5.5067. Min Act: -0.0000

Data Index: 1263540 (C4 (Web Text))

Max Activating Token Index: 209

Text #11

Max Range: 6.7735. Min Range: -6.7735

Max Act: 5.4907. Min Act: -0.0000

Data Index: 449615 (C4 (Web Text))

Max Activating Token Index: 249

Text #12

Max Range: 6.7735. Min Range: -6.7735

Max Act: 5.4923. Min Act: -0.0000

Data Index: 582207 (C4 (Web Text))

Max Activating Token Index: 198

Text #13

Max Range: 6.7735. Min Range: -6.7735

Max Act: 5.3258. Min Act: -0.0000

Data Index: 556640 (C4 (Web Text))

Max Activating Token Index: 336

Text #14

Max Range: 6.7735. Min Range: -6.7735

Max Act: 5.6826. Min Act: -0.0000

Data Index: 1121963 (C4 (Web Text))

Max Activating Token Index: 178

Text #15

Max Range: 6.7735. Min Range: -6.7735

Max Act: 5.5006. Min Act: -0.0000

Data Index: 1270419 (C4 (Web Text))

Max Activating Token Index: 233

Text #16

Max Range: 6.7735. Min Range: -6.7735

Max Act: 5.6852. Min Act: -0.0000

Data Index: 1237194 (C4 (Web Text))

Max Activating Token Index: 331

Text #17

Max Range: 6.7735. Min Range: -6.7735

Max Act: 5.4958. Min Act: -0.0000

Data Index: 809824 (C4 (Web Text))

Max Activating Token Index: 960

Text #18

Max Range: 6.7735. Min Range: -6.7735

Max Act: 5.3060. Min Act: -0.0000

Data Index: 235371 (C4 (Web Text))

Max Activating Token Index: 243

Text #19

Max Range: 6.7735. Min Range: -6.7735

Max Act: 5.6429. Min Act: -0.0000

Data Index: 1113482 (C4 (Web Text))

Max Activating Token Index: 993