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

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

Neuron 1394 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: 0.7226. Min Range: -0.7226

Max Act: 0.7226. Min Act: -0.0000

Data Index: 1288005 (C4 (Web Text))

Max Activating Token Index: 58

Text #1

Max Range: 0.7226. Min Range: -0.7226

Max Act: 0.6286. Min Act: -0.0000

Data Index: 623292 (C4 (Web Text))

Max Activating Token Index: 531

Text #2

Max Range: 0.7226. Min Range: -0.7226

Max Act: 0.6449. Min Act: 0.0000

Data Index: 14226 (C4 (Web Text))

Max Activating Token Index: 317

Text #3

Max Range: 0.7226. Min Range: -0.7226

Max Act: 0.5177. Min Act: -0.0000

Data Index: 697851 (C4 (Web Text))

Max Activating Token Index: 189

Text #4

Max Range: 0.7226. Min Range: -0.7226

Max Act: 0.5957. Min Act: 0.0000

Data Index: 9495 (C4 (Web Text))

Max Activating Token Index: 680

Text #5

Max Range: 0.7226. Min Range: -0.7226

Max Act: 0.5967. Min Act: -0.0000

Data Index: 199333 (C4 (Web Text))

Max Activating Token Index: 493

Text #6

Max Range: 0.7226. Min Range: -0.7226

Max Act: 0.5611. Min Act: -0.0000

Data Index: 225576 (C4 (Web Text))

Max Activating Token Index: 189

Text #7

Max Range: 0.7226. Min Range: -0.7226

Max Act: 0.5576. Min Act: -0.0000

Data Index: 837726 (C4 (Web Text))

Max Activating Token Index: 726

Text #8

Max Range: 0.7226. Min Range: -0.7226

Max Act: 0.5498. Min Act: 0.0001

Data Index: 129128 (C4 (Web Text))

Max Activating Token Index: 661

Text #9

Max Range: 0.7226. Min Range: -0.7226

Max Act: 0.5497. Min Act: -0.0000

Data Index: 835449 (C4 (Web Text))

Max Activating Token Index: 1020

Text #10

Max Range: 0.7226. Min Range: -0.7226

Max Act: 0.5350. Min Act: -0.0000

Data Index: 48352 (C4 (Web Text))

Max Activating Token Index: 564

Text #11

Max Range: 0.7226. Min Range: -0.7226

Max Act: 0.5369. Min Act: -0.0000

Data Index: 1177206 (C4 (Web Text))

Max Activating Token Index: 765

Text #12

Max Range: 0.7226. Min Range: -0.7226

Max Act: 0.5116. Min Act: -0.0000

Data Index: 826864 (C4 (Web Text))

Max Activating Token Index: 501

Text #13

Max Range: 0.7226. Min Range: -0.7226

Max Act: 0.5158. Min Act: -0.0000

Data Index: 815168 (C4 (Web Text))

Max Activating Token Index: 597

Text #14

Max Range: 0.7226. Min Range: -0.7226

Max Act: 0.5147. Min Act: -0.0000

Data Index: 1592057 (Python Code)

Max Activating Token Index: 684

Text #15

Max Range: 0.7226. Min Range: -0.7226

Max Act: 0.4972. Min Act: -0.0000

Data Index: 82605 (C4 (Web Text))

Max Activating Token Index: 526

Text #16

Max Range: 0.7226. Min Range: -0.7226

Max Act: 0.5108. Min Act: -0.0000

Data Index: 89510 (C4 (Web Text))

Max Activating Token Index: 547

Text #17

Max Range: 0.7226. Min Range: -0.7226

Max Act: 0.4271. Min Act: -0.0000

Data Index: 690541 (C4 (Web Text))

Max Activating Token Index: 252

Text #18

Max Range: 0.7226. Min Range: -0.7226

Max Act: 0.5066. Min Act: -0.0000

Data Index: 1461560 (Python Code)

Max Activating Token Index: 822

Text #19

Max Range: 0.7226. Min Range: -0.7226

Max Act: 0.4793. Min Act: -0.0000

Data Index: 564139 (C4 (Web Text))

Max Activating Token Index: 589