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

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

Neuron 146 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6847. Min Range: -0.6847

Max Act: 0.6847. Min Act: -0.0000

Data Index: 342571 (C4 (Web Text))

Max Activating Token Index: 498

Text #1

Max Range: 0.6847. Min Range: -0.6847

Max Act: 0.6335. Min Act: -0.0000

Data Index: 803704 (C4 (Web Text))

Max Activating Token Index: 979

Text #2

Max Range: 0.6847. Min Range: -0.6847

Max Act: 0.6377. Min Act: -0.0000

Data Index: 886181 (C4 (Web Text))

Max Activating Token Index: 494

Text #3

Max Range: 0.6847. Min Range: -0.6847

Max Act: 0.6005. Min Act: -0.0000

Data Index: 1178711 (C4 (Web Text))

Max Activating Token Index: 922

Text #4

Max Range: 0.6847. Min Range: -0.6847

Max Act: 0.5492. Min Act: -0.0000

Data Index: 177149 (C4 (Web Text))

Max Activating Token Index: 791

Text #5

Max Range: 0.6847. Min Range: -0.6847

Max Act: 0.5252. Min Act: -0.0000

Data Index: 465131 (C4 (Web Text))

Max Activating Token Index: 324

Text #6

Max Range: 0.6847. Min Range: -0.6847

Max Act: 0.5541. Min Act: -0.0000

Data Index: 326918 (C4 (Web Text))

Max Activating Token Index: 482

Text #7

Max Range: 0.6847. Min Range: -0.6847

Max Act: 0.4790. Min Act: -0.0000

Data Index: 235368 (C4 (Web Text))

Max Activating Token Index: 999

Text #8

Max Range: 0.6847. Min Range: -0.6847

Max Act: 0.4787. Min Act: -0.0000

Data Index: 496462 (C4 (Web Text))

Max Activating Token Index: 464

Text #9

Max Range: 0.6847. Min Range: -0.6847

Max Act: 0.5004. Min Act: -0.0000

Data Index: 265139 (C4 (Web Text))

Max Activating Token Index: 733

Text #10

Max Range: 0.6847. Min Range: -0.6847

Max Act: 0.4907. Min Act: -0.0000

Data Index: 77584 (C4 (Web Text))

Max Activating Token Index: 27

Text #11

Max Range: 0.6847. Min Range: -0.6847

Max Act: 0.5176. Min Act: -0.0000

Data Index: 1112447 (C4 (Web Text))

Max Activating Token Index: 260

Text #12

Max Range: 0.6847. Min Range: -0.6847

Max Act: 0.4949. Min Act: -0.0000

Data Index: 371209 (C4 (Web Text))

Max Activating Token Index: 367

Text #13

Max Range: 0.6847. Min Range: -0.6847

Max Act: 0.4789. Min Act: -0.0000

Data Index: 580239 (C4 (Web Text))

Max Activating Token Index: 905

Text #14

Max Range: 0.6847. Min Range: -0.6847

Max Act: 0.5136. Min Act: 0.0000

Data Index: 1333696 (C4 (Web Text))

Max Activating Token Index: 295

Text #15

Max Range: 0.6847. Min Range: -0.6847

Max Act: 0.4113. Min Act: -0.0000

Data Index: 405494 (C4 (Web Text))

Max Activating Token Index: 128

Text #16

Max Range: 0.6847. Min Range: -0.6847

Max Act: 0.4910. Min Act: -0.0000

Data Index: 1178665 (C4 (Web Text))

Max Activating Token Index: 935

Text #17

Max Range: 0.6847. Min Range: -0.6847

Max Act: 0.4588. Min Act: -0.0000

Data Index: 1119231 (C4 (Web Text))

Max Activating Token Index: 80

Text #18

Max Range: 0.6847. Min Range: -0.6847

Max Act: 0.4530. Min Act: -0.0000

Data Index: 1120519 (C4 (Web Text))

Max Activating Token Index: 975

Text #19

Max Range: 0.6847. Min Range: -0.6847

Max Act: 0.4265. Min Act: -0.0000

Data Index: 753029 (C4 (Web Text))

Max Activating Token Index: 201