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

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

Neuron 4476 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.2524. Min Range: -6.2524

Max Act: 6.2524. Min Act: -0.0000

Data Index: 488837 (C4 (Web Text))

Max Activating Token Index: 733

Text #1

Max Range: 6.2524. Min Range: -6.2524

Max Act: 5.5546. Min Act: -0.0000

Data Index: 571238 (C4 (Web Text))

Max Activating Token Index: 482

Text #2

Max Range: 6.2524. Min Range: -6.2524

Max Act: 5.4998. Min Act: -0.0000

Data Index: 131985 (C4 (Web Text))

Max Activating Token Index: 596

Text #3

Max Range: 6.2524. Min Range: -6.2524

Max Act: 5.1347. Min Act: -0.0000

Data Index: 286623 (C4 (Web Text))

Max Activating Token Index: 535

Text #4

Max Range: 6.2524. Min Range: -6.2524

Max Act: 5.0629. Min Act: -0.0000

Data Index: 1142061 (C4 (Web Text))

Max Activating Token Index: 93

Text #5

Max Range: 6.2524. Min Range: -6.2524

Max Act: 4.7199. Min Act: -0.0000

Data Index: 499162 (C4 (Web Text))

Max Activating Token Index: 1020

Text #6

Max Range: 6.2524. Min Range: -6.2524

Max Act: 5.0910. Min Act: -0.0000

Data Index: 879730 (C4 (Web Text))

Max Activating Token Index: 822

Text #7

Max Range: 6.2524. Min Range: -6.2524

Max Act: 4.9989. Min Act: -0.0000

Data Index: 669684 (C4 (Web Text))

Max Activating Token Index: 501

Text #8

Max Range: 6.2524. Min Range: -6.2524

Max Act: 4.8431. Min Act: -0.0000

Data Index: 986141 (C4 (Web Text))

Max Activating Token Index: 190

Text #9

Max Range: 6.2524. Min Range: -6.2524

Max Act: 4.5002. Min Act: -0.0000

Data Index: 629021 (C4 (Web Text))

Max Activating Token Index: 152

Text #10

Max Range: 6.2524. Min Range: -6.2524

Max Act: 4.8609. Min Act: -0.0000

Data Index: 114769 (C4 (Web Text))

Max Activating Token Index: 421

Text #11

Max Range: 6.2524. Min Range: -6.2524

Max Act: 4.9068. Min Act: -0.0000

Data Index: 781513 (C4 (Web Text))

Max Activating Token Index: 337

Text #12

Max Range: 6.2524. Min Range: -6.2524

Max Act: 3.7670. Min Act: -0.0000

Data Index: 1119428 (C4 (Web Text))

Max Activating Token Index: 855

Text #13

Max Range: 6.2524. Min Range: -6.2524

Max Act: 4.2840. Min Act: -0.0000

Data Index: 360993 (C4 (Web Text))

Max Activating Token Index: 180

Text #14

Max Range: 6.2524. Min Range: -6.2524

Max Act: 4.4820. Min Act: -0.0000

Data Index: 468413 (C4 (Web Text))

Max Activating Token Index: 925

Text #15

Max Range: 6.2524. Min Range: -6.2524

Max Act: 4.0178. Min Act: -0.0000

Data Index: 1113453 (C4 (Web Text))

Max Activating Token Index: 679

Text #16

Max Range: 6.2524. Min Range: -6.2524

Max Act: 4.3006. Min Act: -0.0000

Data Index: 436274 (C4 (Web Text))

Max Activating Token Index: 61

Text #17

Max Range: 6.2524. Min Range: -6.2524

Max Act: 4.2832. Min Act: -0.0000

Data Index: 134825 (C4 (Web Text))

Max Activating Token Index: 452

Text #18

Max Range: 6.2524. Min Range: -6.2524

Max Act: 4.1383. Min Act: -0.0000

Data Index: 98662 (C4 (Web Text))

Max Activating Token Index: 886

Text #19

Max Range: 6.2524. Min Range: -6.2524

Max Act: 4.1163. Min Act: -0.0000

Data Index: 940855 (C4 (Web Text))

Max Activating Token Index: 396