Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5178 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.2186. Min Range: -3.2186

Max Act: 3.2186. Min Act: -0.0000

Data Index: 1246828 (C4 (Web Text))

Max Activating Token Index: 583

Text #1

Max Range: 3.2186. Min Range: -3.2186

Max Act: 2.2056. Min Act: -0.0000

Data Index: 1508924 (Python Code)

Max Activating Token Index: 434

Text #2

Max Range: 3.2186. Min Range: -3.2186

Max Act: 2.2442. Min Act: -0.0000

Data Index: 1059884 (C4 (Web Text))

Max Activating Token Index: 611

Text #3

Max Range: 3.2186. Min Range: -3.2186

Max Act: 2.2816. Min Act: -0.0000

Data Index: 363716 (C4 (Web Text))

Max Activating Token Index: 413

Text #4

Max Range: 3.2186. Min Range: -3.2186

Max Act: 2.2836. Min Act: -0.0000

Data Index: 1111109 (C4 (Web Text))

Max Activating Token Index: 649

Text #5

Max Range: 3.2186. Min Range: -3.2186

Max Act: 2.4245. Min Act: -0.0000

Data Index: 333785 (C4 (Web Text))

Max Activating Token Index: 251

Text #6

Max Range: 3.2186. Min Range: -3.2186

Max Act: 2.2618. Min Act: -0.0000

Data Index: 23544 (C4 (Web Text))

Max Activating Token Index: 847

Text #7

Max Range: 3.2186. Min Range: -3.2186

Max Act: 2.2610. Min Act: -0.0000

Data Index: 468807 (C4 (Web Text))

Max Activating Token Index: 523

Text #8

Max Range: 3.2186. Min Range: -3.2186

Max Act: 2.1177. Min Act: -0.0000

Data Index: 1563226 (Python Code)

Max Activating Token Index: 748

Text #9

Max Range: 3.2186. Min Range: -3.2186

Max Act: 2.2234. Min Act: -0.0000

Data Index: 1060286 (C4 (Web Text))

Max Activating Token Index: 254

Text #10

Max Range: 3.2186. Min Range: -3.2186

Max Act: 2.1822. Min Act: -0.0000

Data Index: 714257 (C4 (Web Text))

Max Activating Token Index: 471

Text #11

Max Range: 3.2186. Min Range: -3.2186

Max Act: 2.2606. Min Act: -0.0000

Data Index: 454928 (C4 (Web Text))

Max Activating Token Index: 533

Text #12

Max Range: 3.2186. Min Range: -3.2186

Max Act: 2.1091. Min Act: -0.0000

Data Index: 1095939 (C4 (Web Text))

Max Activating Token Index: 216

Text #13

Max Range: 3.2186. Min Range: -3.2186

Max Act: 2.0112. Min Act: -0.0000

Data Index: 150952 (C4 (Web Text))

Max Activating Token Index: 218

Text #14

Max Range: 3.2186. Min Range: -3.2186

Max Act: 2.2085. Min Act: -0.0000

Data Index: 199127 (C4 (Web Text))

Max Activating Token Index: 318

Text #15

Max Range: 3.2186. Min Range: -3.2186

Max Act: 2.0990. Min Act: -0.0000

Data Index: 787544 (C4 (Web Text))

Max Activating Token Index: 770

Text #16

Max Range: 3.2186. Min Range: -3.2186

Max Act: 1.9959. Min Act: -0.0000

Data Index: 234285 (C4 (Web Text))

Max Activating Token Index: 742

Text #17

Max Range: 3.2186. Min Range: -3.2186

Max Act: 2.0893. Min Act: -0.0000

Data Index: 307971 (C4 (Web Text))

Max Activating Token Index: 210

Text #18

Max Range: 3.2186. Min Range: -3.2186

Max Act: 2.0925. Min Act: -0.0000

Data Index: 523948 (C4 (Web Text))

Max Activating Token Index: 806

Text #19

Max Range: 3.2186. Min Range: -3.2186

Max Act: 2.0676. Min Act: -0.0000

Data Index: 536208 (C4 (Web Text))

Max Activating Token Index: 310