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

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

Neuron 3784 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6159. Min Range: -1.6159

Max Act: 1.6159. Min Act: -0.0001

Data Index: 1504686 (Python Code)

Max Activating Token Index: 225

Text #1

Max Range: 1.6159. Min Range: -1.6159

Max Act: 1.4701. Min Act: -0.0001

Data Index: 1461772 (Python Code)

Max Activating Token Index: 778

Text #2

Max Range: 1.6159. Min Range: -1.6159

Max Act: 1.5234. Min Act: -0.0001

Data Index: 1525739 (Python Code)

Max Activating Token Index: 115

Text #3

Max Range: 1.6159. Min Range: -1.6159

Max Act: 1.4078. Min Act: -0.0001

Data Index: 1517683 (Python Code)

Max Activating Token Index: 145

Text #4

Max Range: 1.6159. Min Range: -1.6159

Max Act: 1.4020. Min Act: -0.0001

Data Index: 1392275 (Python Code)

Max Activating Token Index: 220

Text #5

Max Range: 1.6159. Min Range: -1.6159

Max Act: 1.3697. Min Act: -0.0001

Data Index: 1368059 (Python Code)

Max Activating Token Index: 121

Text #6

Max Range: 1.6159. Min Range: -1.6159

Max Act: 1.1723. Min Act: -0.0001

Data Index: 1646225 (Python Code)

Max Activating Token Index: 153

Text #7

Max Range: 1.6159. Min Range: -1.6159

Max Act: 1.2719. Min Act: -0.0001

Data Index: 1649761 (Python Code)

Max Activating Token Index: 730

Text #8

Max Range: 1.6159. Min Range: -1.6159

Max Act: 1.2496. Min Act: -0.0001

Data Index: 1485640 (Python Code)

Max Activating Token Index: 164

Text #9

Max Range: 1.6159. Min Range: -1.6159

Max Act: 1.2790. Min Act: -0.0001

Data Index: 1546477 (Python Code)

Max Activating Token Index: 601

Text #10

Max Range: 1.6159. Min Range: -1.6159

Max Act: 1.2401. Min Act: -0.0001

Data Index: 1583119 (Python Code)

Max Activating Token Index: 439

Text #11

Max Range: 1.6159. Min Range: -1.6159

Max Act: 1.2384. Min Act: -0.0001

Data Index: 1543176 (Python Code)

Max Activating Token Index: 729

Text #12

Max Range: 1.6159. Min Range: -1.6159

Max Act: 1.2628. Min Act: -0.0001

Data Index: 1561141 (Python Code)

Max Activating Token Index: 752

Text #13

Max Range: 1.6159. Min Range: -1.6159

Max Act: 1.1364. Min Act: -0.0001

Data Index: 1581444 (Python Code)

Max Activating Token Index: 191

Text #14

Max Range: 1.6159. Min Range: -1.6159

Max Act: 1.2008. Min Act: -0.0000

Data Index: 1361368 (Python Code)

Max Activating Token Index: 537

Text #15

Max Range: 1.6159. Min Range: -1.6159

Max Act: 1.1918. Min Act: -0.0001

Data Index: 1417273 (Python Code)

Max Activating Token Index: 551

Text #16

Max Range: 1.6159. Min Range: -1.6159

Max Act: 1.1545. Min Act: -0.0001

Data Index: 1532717 (Python Code)

Max Activating Token Index: 842

Text #17

Max Range: 1.6159. Min Range: -1.6159

Max Act: 1.1891. Min Act: -0.0001

Data Index: 1545232 (Python Code)

Max Activating Token Index: 525

Text #18

Max Range: 1.6159. Min Range: -1.6159

Max Act: 1.2017. Min Act: -0.0001

Data Index: 1504204 (Python Code)

Max Activating Token Index: 62

Text #19

Max Range: 1.6159. Min Range: -1.6159

Max Act: 1.1299. Min Act: -0.0001

Data Index: 1465339 (Python Code)

Max Activating Token Index: 973