Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1832 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.4731. Min Range: -0.4731

Max Act: 0.4731. Min Act: -0.0003

Data Index: 1268718 (C4 (Web Text))

Max Activating Token Index: 348

Text #1

Max Range: 0.4731. Min Range: -0.4731

Max Act: 0.4344. Min Act: -0.0003

Data Index: 79304 (C4 (Web Text))

Max Activating Token Index: 923

Text #2

Max Range: 0.4731. Min Range: -0.4731

Max Act: 0.3902. Min Act: -0.0003

Data Index: 330705 (C4 (Web Text))

Max Activating Token Index: 844

Text #3

Max Range: 0.4731. Min Range: -0.4731

Max Act: 0.3833. Min Act: -0.0003

Data Index: 894733 (C4 (Web Text))

Max Activating Token Index: 526

Text #4

Max Range: 0.4731. Min Range: -0.4731

Max Act: 0.3648. Min Act: -0.0003

Data Index: 393178 (C4 (Web Text))

Max Activating Token Index: 761

Text #5

Max Range: 0.4731. Min Range: -0.4731

Max Act: 0.3394. Min Act: -0.0003

Data Index: 120985 (C4 (Web Text))

Max Activating Token Index: 439

Text #6

Max Range: 0.4731. Min Range: -0.4731

Max Act: 0.3599. Min Act: -0.0003

Data Index: 1168709 (C4 (Web Text))

Max Activating Token Index: 506

Text #7

Max Range: 0.4731. Min Range: -0.4731

Max Act: 0.3561. Min Act: -0.0003

Data Index: 515324 (C4 (Web Text))

Max Activating Token Index: 330

Text #8

Max Range: 0.4731. Min Range: -0.4731

Max Act: 0.3504. Min Act: -0.0003

Data Index: 1171362 (C4 (Web Text))

Max Activating Token Index: 505

Text #9

Max Range: 0.4731. Min Range: -0.4731

Max Act: 0.3487. Min Act: -0.0003

Data Index: 1146138 (C4 (Web Text))

Max Activating Token Index: 424

Text #10

Max Range: 0.4731. Min Range: -0.4731

Max Act: 0.3377. Min Act: -0.0003

Data Index: 886931 (C4 (Web Text))

Max Activating Token Index: 602

Text #11

Max Range: 0.4731. Min Range: -0.4731

Max Act: 0.3334. Min Act: -0.0003

Data Index: 645229 (C4 (Web Text))

Max Activating Token Index: 387

Text #12

Max Range: 0.4731. Min Range: -0.4731

Max Act: 0.3180. Min Act: -0.0003

Data Index: 1321317 (C4 (Web Text))

Max Activating Token Index: 390

Text #13

Max Range: 0.4731. Min Range: -0.4731

Max Act: 0.3119. Min Act: -0.0002

Data Index: 395194 (C4 (Web Text))

Max Activating Token Index: 437

Text #14

Max Range: 0.4731. Min Range: -0.4731

Max Act: 0.3082. Min Act: -0.0003

Data Index: 571414 (C4 (Web Text))

Max Activating Token Index: 271

Text #15

Max Range: 0.4731. Min Range: -0.4731

Max Act: 0.3077. Min Act: -0.0003

Data Index: 788155 (C4 (Web Text))

Max Activating Token Index: 371

Text #16

Max Range: 0.4731. Min Range: -0.4731

Max Act: 0.3072. Min Act: -0.0003

Data Index: 1315304 (C4 (Web Text))

Max Activating Token Index: 39

Text #17

Max Range: 0.4731. Min Range: -0.4731

Max Act: 0.3068. Min Act: -0.0003

Data Index: 339188 (C4 (Web Text))

Max Activating Token Index: 161

Text #18

Max Range: 0.4731. Min Range: -0.4731

Max Act: 0.3274. Min Act: -0.0003

Data Index: 407466 (C4 (Web Text))

Max Activating Token Index: 847

Text #19

Max Range: 0.4731. Min Range: -0.4731

Max Act: 0.3052. Min Act: -0.0003

Data Index: 571389 (C4 (Web Text))

Max Activating Token Index: 211