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

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

Neuron 3566 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3929. Min Range: -0.3929

Max Act: 0.3929. Min Act: -0.0000

Data Index: 1290014 (C4 (Web Text))

Max Activating Token Index: 647

Text #1

Max Range: 0.3929. Min Range: -0.3929

Max Act: 0.3180. Min Act: -0.0000

Data Index: 349104 (C4 (Web Text))

Max Activating Token Index: 837

Text #2

Max Range: 0.3929. Min Range: -0.3929

Max Act: 0.2545. Min Act: -0.0000

Data Index: 493460 (C4 (Web Text))

Max Activating Token Index: 84

Text #3

Max Range: 0.3929. Min Range: -0.3929

Max Act: 0.2631. Min Act: -0.0000

Data Index: 1103833 (C4 (Web Text))

Max Activating Token Index: 332

Text #4

Max Range: 0.3929. Min Range: -0.3929

Max Act: 0.2072. Min Act: -0.0000

Data Index: 676870 (C4 (Web Text))

Max Activating Token Index: 200

Text #5

Max Range: 0.3929. Min Range: -0.3929

Max Act: 0.2454. Min Act: -0.0000

Data Index: 901271 (C4 (Web Text))

Max Activating Token Index: 410

Text #6

Max Range: 0.3929. Min Range: -0.3929

Max Act: 0.2464. Min Act: -0.0000

Data Index: 1287176 (C4 (Web Text))

Max Activating Token Index: 1008

Text #7

Max Range: 0.3929. Min Range: -0.3929

Max Act: 0.2343. Min Act: -0.0000

Data Index: 640798 (C4 (Web Text))

Max Activating Token Index: 432

Text #8

Max Range: 0.3929. Min Range: -0.3929

Max Act: 0.2310. Min Act: -0.0000

Data Index: 1200534 (C4 (Web Text))

Max Activating Token Index: 414

Text #9

Max Range: 0.3929. Min Range: -0.3929

Max Act: 0.2122. Min Act: -0.0000

Data Index: 340422 (C4 (Web Text))

Max Activating Token Index: 821

Text #10

Max Range: 0.3929. Min Range: -0.3929

Max Act: 0.2225. Min Act: -0.0000

Data Index: 758572 (C4 (Web Text))

Max Activating Token Index: 671

Text #11

Max Range: 0.3929. Min Range: -0.3929

Max Act: 0.2084. Min Act: -0.0000

Data Index: 459646 (C4 (Web Text))

Max Activating Token Index: 427

Text #12

Max Range: 0.3929. Min Range: -0.3929

Max Act: 0.2236. Min Act: -0.0000

Data Index: 926006 (C4 (Web Text))

Max Activating Token Index: 523

Text #13

Max Range: 0.3929. Min Range: -0.3929

Max Act: 0.2221. Min Act: -0.0000

Data Index: 434545 (C4 (Web Text))

Max Activating Token Index: 526

Text #14

Max Range: 0.3929. Min Range: -0.3929

Max Act: 0.2041. Min Act: -0.0000

Data Index: 1063292 (C4 (Web Text))

Max Activating Token Index: 204

Text #15

Max Range: 0.3929. Min Range: -0.3929

Max Act: 0.2006. Min Act: -0.0000

Data Index: 1167003 (C4 (Web Text))

Max Activating Token Index: 214

Text #16

Max Range: 0.3929. Min Range: -0.3929

Max Act: 0.1986. Min Act: -0.0000

Data Index: 258912 (C4 (Web Text))

Max Activating Token Index: 927

Text #17

Max Range: 0.3929. Min Range: -0.3929

Max Act: 0.2113. Min Act: -0.0000

Data Index: 438268 (C4 (Web Text))

Max Activating Token Index: 618

Text #18

Max Range: 0.3929. Min Range: -0.3929

Max Act: 0.2106. Min Act: -0.0000

Data Index: 1248945 (C4 (Web Text))

Max Activating Token Index: 479

Text #19

Max Range: 0.3929. Min Range: -0.3929

Max Act: 0.1938. Min Act: -0.0000

Data Index: 649767 (C4 (Web Text))

Max Activating Token Index: 611