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

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

Neuron 4233 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6350. Min Range: -0.6350

Max Act: 0.6350. Min Act: -0.0000

Data Index: 268233 (C4 (Web Text))

Max Activating Token Index: 7

Text #1

Max Range: 0.6350. Min Range: -0.6350

Max Act: 0.5788. Min Act: -0.0000

Data Index: 222849 (C4 (Web Text))

Max Activating Token Index: 349

Text #2

Max Range: 0.6350. Min Range: -0.6350

Max Act: 0.5561. Min Act: -0.0000

Data Index: 627083 (C4 (Web Text))

Max Activating Token Index: 233

Text #3

Max Range: 0.6350. Min Range: -0.6350

Max Act: 0.5593. Min Act: -0.0000

Data Index: 483811 (C4 (Web Text))

Max Activating Token Index: 229

Text #4

Max Range: 0.6350. Min Range: -0.6350

Max Act: 0.5324. Min Act: -0.0000

Data Index: 126992 (C4 (Web Text))

Max Activating Token Index: 440

Text #5

Max Range: 0.6350. Min Range: -0.6350

Max Act: 0.5570. Min Act: -0.0000

Data Index: 1263201 (C4 (Web Text))

Max Activating Token Index: 609

Text #6

Max Range: 0.6350. Min Range: -0.6350

Max Act: 0.5676. Min Act: -0.0000

Data Index: 688946 (C4 (Web Text))

Max Activating Token Index: 314

Text #7

Max Range: 0.6350. Min Range: -0.6350

Max Act: 0.5241. Min Act: -0.0000

Data Index: 92888 (C4 (Web Text))

Max Activating Token Index: 270

Text #8

Max Range: 0.6350. Min Range: -0.6350

Max Act: 0.5764. Min Act: -0.0000

Data Index: 109525 (C4 (Web Text))

Max Activating Token Index: 321

Text #9

Max Range: 0.6350. Min Range: -0.6350

Max Act: 0.4904. Min Act: -0.0000

Data Index: 954364 (C4 (Web Text))

Max Activating Token Index: 370

Text #10

Max Range: 0.6350. Min Range: -0.6350

Max Act: 0.5248. Min Act: -0.0000

Data Index: 669394 (C4 (Web Text))

Max Activating Token Index: 310

Text #11

Max Range: 0.6350. Min Range: -0.6350

Max Act: 0.5087. Min Act: -0.0000

Data Index: 387168 (C4 (Web Text))

Max Activating Token Index: 168

Text #12

Max Range: 0.6350. Min Range: -0.6350

Max Act: 0.5057. Min Act: -0.0000

Data Index: 545456 (C4 (Web Text))

Max Activating Token Index: 501

Text #13

Max Range: 0.6350. Min Range: -0.6350

Max Act: 0.5145. Min Act: -0.0000

Data Index: 140938 (C4 (Web Text))

Max Activating Token Index: 444

Text #14

Max Range: 0.6350. Min Range: -0.6350

Max Act: 0.5141. Min Act: -0.0000

Data Index: 224194 (C4 (Web Text))

Max Activating Token Index: 119

Text #15

Max Range: 0.6350. Min Range: -0.6350

Max Act: 0.5148. Min Act: -0.0000

Data Index: 59722 (C4 (Web Text))

Max Activating Token Index: 81

Text #16

Max Range: 0.6350. Min Range: -0.6350

Max Act: 0.5197. Min Act: -0.0000

Data Index: 311674 (C4 (Web Text))

Max Activating Token Index: 465

Text #17

Max Range: 0.6350. Min Range: -0.6350

Max Act: 0.5500. Min Act: -0.0000

Data Index: 438466 (C4 (Web Text))

Max Activating Token Index: 795

Text #18

Max Range: 0.6350. Min Range: -0.6350

Max Act: 0.4777. Min Act: -0.0000

Data Index: 1150919 (C4 (Web Text))

Max Activating Token Index: 461

Text #19

Max Range: 0.6350. Min Range: -0.6350

Max Act: 0.4929. Min Act: -0.0000

Data Index: 702503 (C4 (Web Text))

Max Activating Token Index: 880