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

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

Neuron 3878 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2475. Min Range: -0.2475

Max Act: 0.2373. Min Act: -0.0001

Data Index: 1531126 (Python Code)

Max Activating Token Index: 762

Text #1

Max Range: 0.2475. Min Range: -0.2475

Max Act: 0.2475. Min Act: -0.0001

Data Index: 278445 (C4 (Web Text))

Max Activating Token Index: 385

Text #2

Max Range: 0.2475. Min Range: -0.2475

Max Act: 0.2169. Min Act: -0.0001

Data Index: 660522 (C4 (Web Text))

Max Activating Token Index: 236

Text #3

Max Range: 0.2475. Min Range: -0.2475

Max Act: 0.2079. Min Act: -0.0001

Data Index: 1151554 (C4 (Web Text))

Max Activating Token Index: 446

Text #4

Max Range: 0.2475. Min Range: -0.2475

Max Act: 0.2013. Min Act: -0.0001

Data Index: 1445165 (Python Code)

Max Activating Token Index: 214

Text #5

Max Range: 0.2475. Min Range: -0.2475

Max Act: 0.2008. Min Act: -0.0001

Data Index: 1621561 (Python Code)

Max Activating Token Index: 635

Text #6

Max Range: 0.2475. Min Range: -0.2475

Max Act: 0.1974. Min Act: -0.0001

Data Index: 478249 (C4 (Web Text))

Max Activating Token Index: 603

Text #7

Max Range: 0.2475. Min Range: -0.2475

Max Act: 0.1944. Min Act: -0.0001

Data Index: 1374040 (Python Code)

Max Activating Token Index: 398

Text #8

Max Range: 0.2475. Min Range: -0.2475

Max Act: 0.1929. Min Act: -0.0001

Data Index: 1540385 (Python Code)

Max Activating Token Index: 37

Text #9

Max Range: 0.2475. Min Range: -0.2475

Max Act: 0.1926. Min Act: -0.0001

Data Index: 1307658 (C4 (Web Text))

Max Activating Token Index: 89

Text #10

Max Range: 0.2475. Min Range: -0.2475

Max Act: 0.1945. Min Act: -0.0001

Data Index: 1457188 (Python Code)

Max Activating Token Index: 210

Text #11

Max Range: 0.2475. Min Range: -0.2475

Max Act: 0.2000. Min Act: -0.0001

Data Index: 1048432 (C4 (Web Text))

Max Activating Token Index: 176

Text #12

Max Range: 0.2475. Min Range: -0.2475

Max Act: 0.1788. Min Act: -0.0001

Data Index: 911042 (C4 (Web Text))

Max Activating Token Index: 164

Text #13

Max Range: 0.2475. Min Range: -0.2475

Max Act: 0.1906. Min Act: -0.0001

Data Index: 46551 (C4 (Web Text))

Max Activating Token Index: 33

Text #14

Max Range: 0.2475. Min Range: -0.2475

Max Act: 0.1791. Min Act: -0.0001

Data Index: 1538604 (Python Code)

Max Activating Token Index: 2

Text #15

Max Range: 0.2475. Min Range: -0.2475

Max Act: 0.1815. Min Act: -0.0001

Data Index: 497261 (C4 (Web Text))

Max Activating Token Index: 179

Text #16

Max Range: 0.2475. Min Range: -0.2475

Max Act: 0.1757. Min Act: -0.0001

Data Index: 695640 (C4 (Web Text))

Max Activating Token Index: 152

Text #17

Max Range: 0.2475. Min Range: -0.2475

Max Act: 0.1837. Min Act: -0.0001

Data Index: 1108700 (C4 (Web Text))

Max Activating Token Index: 394

Text #18

Max Range: 0.2475. Min Range: -0.2475

Max Act: 0.1748. Min Act: -0.0001

Data Index: 86513 (C4 (Web Text))

Max Activating Token Index: 159

Text #19

Max Range: 0.2475. Min Range: -0.2475

Max Act: 0.1942. Min Act: -0.0001

Data Index: 1433947 (Python Code)

Max Activating Token Index: 555