Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1535 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.2776. Min Range: -0.2776

Max Act: 0.2776. Min Act: -0.0001

Data Index: 1367643 (Python Code)

Max Activating Token Index: 210

Text #1

Max Range: 0.2776. Min Range: -0.2776

Max Act: 0.2390. Min Act: -0.0001

Data Index: 400602 (C4 (Web Text))

Max Activating Token Index: 49

Text #2

Max Range: 0.2776. Min Range: -0.2776

Max Act: 0.2459. Min Act: -0.0001

Data Index: 159790 (C4 (Web Text))

Max Activating Token Index: 392

Text #3

Max Range: 0.2776. Min Range: -0.2776

Max Act: 0.2494. Min Act: -0.0001

Data Index: 491845 (C4 (Web Text))

Max Activating Token Index: 373

Text #4

Max Range: 0.2776. Min Range: -0.2776

Max Act: 0.2426. Min Act: -0.0001

Data Index: 580441 (C4 (Web Text))

Max Activating Token Index: 201

Text #5

Max Range: 0.2776. Min Range: -0.2776

Max Act: 0.2095. Min Act: -0.0001

Data Index: 298341 (C4 (Web Text))

Max Activating Token Index: 590

Text #6

Max Range: 0.2776. Min Range: -0.2776

Max Act: 0.2162. Min Act: -0.0001

Data Index: 684675 (C4 (Web Text))

Max Activating Token Index: 452

Text #7

Max Range: 0.2776. Min Range: -0.2776

Max Act: 0.2182. Min Act: -0.0001

Data Index: 663288 (C4 (Web Text))

Max Activating Token Index: 161

Text #8

Max Range: 0.2776. Min Range: -0.2776

Max Act: 0.2191. Min Act: -0.0001

Data Index: 1341281 (C4 (Web Text))

Max Activating Token Index: 334

Text #9

Max Range: 0.2776. Min Range: -0.2776

Max Act: 0.1997. Min Act: -0.0001

Data Index: 223075 (C4 (Web Text))

Max Activating Token Index: 122

Text #10

Max Range: 0.2776. Min Range: -0.2776

Max Act: 0.1998. Min Act: -0.0001

Data Index: 132896 (C4 (Web Text))

Max Activating Token Index: 525

Text #11

Max Range: 0.2776. Min Range: -0.2776

Max Act: 0.1940. Min Act: -0.0001

Data Index: 1030804 (C4 (Web Text))

Max Activating Token Index: 786

Text #12

Max Range: 0.2776. Min Range: -0.2776

Max Act: 0.2144. Min Act: -0.0001

Data Index: 1284140 (C4 (Web Text))

Max Activating Token Index: 33

Text #13

Max Range: 0.2776. Min Range: -0.2776

Max Act: 0.2073. Min Act: -0.0001

Data Index: 321313 (C4 (Web Text))

Max Activating Token Index: 525

Text #14

Max Range: 0.2776. Min Range: -0.2776

Max Act: 0.2063. Min Act: -0.0001

Data Index: 642485 (C4 (Web Text))

Max Activating Token Index: 180

Text #15

Max Range: 0.2776. Min Range: -0.2776

Max Act: 0.1987. Min Act: -0.0001

Data Index: 1208744 (C4 (Web Text))

Max Activating Token Index: 808

Text #16

Max Range: 0.2776. Min Range: -0.2776

Max Act: 0.1975. Min Act: -0.0001

Data Index: 199957 (C4 (Web Text))

Max Activating Token Index: 45

Text #17

Max Range: 0.2776. Min Range: -0.2776

Max Act: 0.1950. Min Act: -0.0001

Data Index: 394545 (C4 (Web Text))

Max Activating Token Index: 33

Text #18

Max Range: 0.2776. Min Range: -0.2776

Max Act: 0.2006. Min Act: -0.0001

Data Index: 477165 (C4 (Web Text))

Max Activating Token Index: 21

Text #19

Max Range: 0.2776. Min Range: -0.2776

Max Act: 0.1986. Min Act: -0.0001

Data Index: 1276680 (C4 (Web Text))

Max Activating Token Index: 57