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

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

Neuron 3115 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8673. Min Range: -0.8673

Max Act: 0.8524. Min Act: -0.0001

Data Index: 1311190 (C4 (Web Text))

Max Activating Token Index: 841

Text #1

Max Range: 0.8673. Min Range: -0.8673

Max Act: 0.8221. Min Act: -0.0001

Data Index: 1077245 (C4 (Web Text))

Max Activating Token Index: 899

Text #2

Max Range: 0.8673. Min Range: -0.8673

Max Act: 0.8370. Min Act: -0.0001

Data Index: 390397 (C4 (Web Text))

Max Activating Token Index: 256

Text #3

Max Range: 0.8673. Min Range: -0.8673

Max Act: 0.8673. Min Act: -0.0001

Data Index: 1155102 (C4 (Web Text))

Max Activating Token Index: 123

Text #4

Max Range: 0.8673. Min Range: -0.8673

Max Act: 0.8222. Min Act: -0.0001

Data Index: 197911 (C4 (Web Text))

Max Activating Token Index: 523

Text #5

Max Range: 0.8673. Min Range: -0.8673

Max Act: 0.7902. Min Act: -0.0001

Data Index: 1117019 (C4 (Web Text))

Max Activating Token Index: 635

Text #6

Max Range: 0.8673. Min Range: -0.8673

Max Act: 0.7909. Min Act: -0.0001

Data Index: 199570 (C4 (Web Text))

Max Activating Token Index: 399

Text #7

Max Range: 0.8673. Min Range: -0.8673

Max Act: 0.8143. Min Act: -0.0001

Data Index: 1306630 (C4 (Web Text))

Max Activating Token Index: 174

Text #8

Max Range: 0.8673. Min Range: -0.8673

Max Act: 0.8133. Min Act: -0.0001

Data Index: 519839 (C4 (Web Text))

Max Activating Token Index: 434

Text #9

Max Range: 0.8673. Min Range: -0.8673

Max Act: 0.7774. Min Act: -0.0001

Data Index: 968337 (C4 (Web Text))

Max Activating Token Index: 991

Text #10

Max Range: 0.8673. Min Range: -0.8673

Max Act: 0.7612. Min Act: -0.0001

Data Index: 876213 (C4 (Web Text))

Max Activating Token Index: 24

Text #11

Max Range: 0.8673. Min Range: -0.8673

Max Act: 0.7623. Min Act: -0.0001

Data Index: 705012 (C4 (Web Text))

Max Activating Token Index: 333

Text #12

Max Range: 0.8673. Min Range: -0.8673

Max Act: 0.7354. Min Act: -0.0001

Data Index: 994474 (C4 (Web Text))

Max Activating Token Index: 277

Text #13

Max Range: 0.8673. Min Range: -0.8673

Max Act: 0.7076. Min Act: -0.0001

Data Index: 1255916 (C4 (Web Text))

Max Activating Token Index: 288

Text #14

Max Range: 0.8673. Min Range: -0.8673

Max Act: 0.7831. Min Act: -0.0001

Data Index: 587047 (C4 (Web Text))

Max Activating Token Index: 364

Text #15

Max Range: 0.8673. Min Range: -0.8673

Max Act: 0.7577. Min Act: -0.0001

Data Index: 241488 (C4 (Web Text))

Max Activating Token Index: 254

Text #16

Max Range: 0.8673. Min Range: -0.8673

Max Act: 0.7485. Min Act: -0.0001

Data Index: 732864 (C4 (Web Text))

Max Activating Token Index: 598

Text #17

Max Range: 0.8673. Min Range: -0.8673

Max Act: 0.7423. Min Act: -0.0001

Data Index: 390498 (C4 (Web Text))

Max Activating Token Index: 880

Text #18

Max Range: 0.8673. Min Range: -0.8673

Max Act: 0.7028. Min Act: -0.0001

Data Index: 429015 (C4 (Web Text))

Max Activating Token Index: 745

Text #19

Max Range: 0.8673. Min Range: -0.8673

Max Act: 0.7007. Min Act: -0.0001

Data Index: 107943 (C4 (Web Text))

Max Activating Token Index: 365