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

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

Neuron 2804 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5916. Min Range: -1.5916

Max Act: 1.5916. Min Act: -0.0000

Data Index: 654807 (C4 (Web Text))

Max Activating Token Index: 131

Text #1

Max Range: 1.5916. Min Range: -1.5916

Max Act: 1.0644. Min Act: -0.0000

Data Index: 638506 (C4 (Web Text))

Max Activating Token Index: 620

Text #2

Max Range: 1.5916. Min Range: -1.5916

Max Act: 1.0257. Min Act: -0.0000

Data Index: 1035431 (C4 (Web Text))

Max Activating Token Index: 80

Text #3

Max Range: 1.5916. Min Range: -1.5916

Max Act: 1.0159. Min Act: -0.0000

Data Index: 1315739 (C4 (Web Text))

Max Activating Token Index: 751

Text #4

Max Range: 1.5916. Min Range: -1.5916

Max Act: 0.9011. Min Act: -0.0000

Data Index: 242407 (C4 (Web Text))

Max Activating Token Index: 308

Text #5

Max Range: 1.5916. Min Range: -1.5916

Max Act: 0.7772. Min Act: -0.0000

Data Index: 1293662 (C4 (Web Text))

Max Activating Token Index: 913

Text #6

Max Range: 1.5916. Min Range: -1.5916

Max Act: 0.7371. Min Act: -0.0000

Data Index: 614313 (C4 (Web Text))

Max Activating Token Index: 919

Text #7

Max Range: 1.5916. Min Range: -1.5916

Max Act: 0.7679. Min Act: -0.0000

Data Index: 230973 (C4 (Web Text))

Max Activating Token Index: 162

Text #8

Max Range: 1.5916. Min Range: -1.5916

Max Act: 0.8806. Min Act: -0.0000

Data Index: 690354 (C4 (Web Text))

Max Activating Token Index: 551

Text #9

Max Range: 1.5916. Min Range: -1.5916

Max Act: 0.5987. Min Act: -0.0000

Data Index: 1030078 (C4 (Web Text))

Max Activating Token Index: 538

Text #10

Max Range: 1.5916. Min Range: -1.5916

Max Act: 0.6660. Min Act: -0.0000

Data Index: 468044 (C4 (Web Text))

Max Activating Token Index: 268

Text #11

Max Range: 1.5916. Min Range: -1.5916

Max Act: 0.5251. Min Act: -0.0000

Data Index: 806927 (C4 (Web Text))

Max Activating Token Index: 990

Text #12

Max Range: 1.5916. Min Range: -1.5916

Max Act: 0.5762. Min Act: -0.0000

Data Index: 485691 (C4 (Web Text))

Max Activating Token Index: 287

Text #13

Max Range: 1.5916. Min Range: -1.5916

Max Act: 0.5300. Min Act: -0.0000

Data Index: 610358 (C4 (Web Text))

Max Activating Token Index: 373

Text #14

Max Range: 1.5916. Min Range: -1.5916

Max Act: 0.5131. Min Act: -0.0000

Data Index: 850631 (C4 (Web Text))

Max Activating Token Index: 577

Text #15

Max Range: 1.5916. Min Range: -1.5916

Max Act: 0.5721. Min Act: -0.0000

Data Index: 292934 (C4 (Web Text))

Max Activating Token Index: 253

Text #16

Max Range: 1.5916. Min Range: -1.5916

Max Act: 0.5419. Min Act: -0.0000

Data Index: 461270 (C4 (Web Text))

Max Activating Token Index: 301

Text #17

Max Range: 1.5916. Min Range: -1.5916

Max Act: 0.4842. Min Act: -0.0000

Data Index: 907175 (C4 (Web Text))

Max Activating Token Index: 609

Text #18

Max Range: 1.5916. Min Range: -1.5916

Max Act: 0.5269. Min Act: -0.0000

Data Index: 55644 (C4 (Web Text))

Max Activating Token Index: 252

Text #19

Max Range: 1.5916. Min Range: -1.5916

Max Act: 0.5250. Min Act: -0.0000

Data Index: 443071 (C4 (Web Text))

Max Activating Token Index: 708