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

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

Neuron 4006 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6896. Min Range: -0.6896

Max Act: 0.6896. Min Act: -0.0000

Data Index: 945064 (C4 (Web Text))

Max Activating Token Index: 923

Text #1

Max Range: 0.6896. Min Range: -0.6896

Max Act: 0.6133. Min Act: -0.0000

Data Index: 126521 (C4 (Web Text))

Max Activating Token Index: 312

Text #2

Max Range: 0.6896. Min Range: -0.6896

Max Act: 0.5839. Min Act: -0.0000

Data Index: 1284924 (C4 (Web Text))

Max Activating Token Index: 448

Text #3

Max Range: 0.6896. Min Range: -0.6896

Max Act: 0.5640. Min Act: -0.0000

Data Index: 1057376 (C4 (Web Text))

Max Activating Token Index: 290

Text #4

Max Range: 0.6896. Min Range: -0.6896

Max Act: 0.5494. Min Act: 0.0000

Data Index: 955290 (C4 (Web Text))

Max Activating Token Index: 145

Text #5

Max Range: 0.6896. Min Range: -0.6896

Max Act: 0.5775. Min Act: -0.0000

Data Index: 482980 (C4 (Web Text))

Max Activating Token Index: 278

Text #6

Max Range: 0.6896. Min Range: -0.6896

Max Act: 0.5304. Min Act: -0.0000

Data Index: 468457 (C4 (Web Text))

Max Activating Token Index: 962

Text #7

Max Range: 0.6896. Min Range: -0.6896

Max Act: 0.5212. Min Act: -0.0000

Data Index: 213575 (C4 (Web Text))

Max Activating Token Index: 659

Text #8

Max Range: 0.6896. Min Range: -0.6896

Max Act: 0.4808. Min Act: -0.0000

Data Index: 845937 (C4 (Web Text))

Max Activating Token Index: 899

Text #9

Max Range: 0.6896. Min Range: -0.6896

Max Act: 0.4821. Min Act: -0.0000

Data Index: 338416 (C4 (Web Text))

Max Activating Token Index: 962

Text #10

Max Range: 0.6896. Min Range: -0.6896

Max Act: 0.4674. Min Act: -0.0000

Data Index: 104833 (C4 (Web Text))

Max Activating Token Index: 595

Text #11

Max Range: 0.6896. Min Range: -0.6896

Max Act: 0.4780. Min Act: -0.0000

Data Index: 449607 (C4 (Web Text))

Max Activating Token Index: 576

Text #12

Max Range: 0.6896. Min Range: -0.6896

Max Act: 0.4423. Min Act: 0.0000

Data Index: 437803 (C4 (Web Text))

Max Activating Token Index: 529

Text #13

Max Range: 0.6896. Min Range: -0.6896

Max Act: 0.4460. Min Act: -0.0000

Data Index: 806740 (C4 (Web Text))

Max Activating Token Index: 911

Text #14

Max Range: 0.6896. Min Range: -0.6896

Max Act: 0.4550. Min Act: -0.0000

Data Index: 820959 (C4 (Web Text))

Max Activating Token Index: 276

Text #15

Max Range: 0.6896. Min Range: -0.6896

Max Act: 0.4202. Min Act: -0.0000

Data Index: 37589 (C4 (Web Text))

Max Activating Token Index: 223

Text #16

Max Range: 0.6896. Min Range: -0.6896

Max Act: 0.4336. Min Act: -0.0000

Data Index: 1279894 (C4 (Web Text))

Max Activating Token Index: 397

Text #17

Max Range: 0.6896. Min Range: -0.6896

Max Act: 0.4134. Min Act: -0.0000

Data Index: 649225 (C4 (Web Text))

Max Activating Token Index: 35

Text #18

Max Range: 0.6896. Min Range: -0.6896

Max Act: 0.4235. Min Act: 0.0000

Data Index: 343708 (C4 (Web Text))

Max Activating Token Index: 348

Text #19

Max Range: 0.6896. Min Range: -0.6896

Max Act: 0.4237. Min Act: -0.0000

Data Index: 1264525 (C4 (Web Text))

Max Activating Token Index: 110