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

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

Neuron 3318 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3765. Min Range: -1.3765

Max Act: 1.3765. Min Act: -0.0001

Data Index: 66386 (C4 (Web Text))

Max Activating Token Index: 39

Text #1

Max Range: 1.3765. Min Range: -1.3765

Max Act: 1.3259. Min Act: -0.0001

Data Index: 1483482 (Python Code)

Max Activating Token Index: 601

Text #2

Max Range: 1.3765. Min Range: -1.3765

Max Act: 1.2226. Min Act: -0.0001

Data Index: 1592290 (Python Code)

Max Activating Token Index: 236

Text #3

Max Range: 1.3765. Min Range: -1.3765

Max Act: 1.1838. Min Act: -0.0001

Data Index: 1206864 (C4 (Web Text))

Max Activating Token Index: 1018

Text #4

Max Range: 1.3765. Min Range: -1.3765

Max Act: 1.1838. Min Act: -0.0000

Data Index: 1514097 (Python Code)

Max Activating Token Index: 387

Text #5

Max Range: 1.3765. Min Range: -1.3765

Max Act: 1.2158. Min Act: -0.0001

Data Index: 1412820 (Python Code)

Max Activating Token Index: 434

Text #6

Max Range: 1.3765. Min Range: -1.3765

Max Act: 1.1706. Min Act: -0.0001

Data Index: 408392 (C4 (Web Text))

Max Activating Token Index: 728

Text #7

Max Range: 1.3765. Min Range: -1.3765

Max Act: 1.1156. Min Act: -0.0001

Data Index: 1361827 (Python Code)

Max Activating Token Index: 769

Text #8

Max Range: 1.3765. Min Range: -1.3765

Max Act: 1.1286. Min Act: -0.0000

Data Index: 1494003 (Python Code)

Max Activating Token Index: 668

Text #9

Max Range: 1.3765. Min Range: -1.3765

Max Act: 1.1147. Min Act: -0.0000

Data Index: 1356233 (C4 (Web Text))

Max Activating Token Index: 424

Text #10

Max Range: 1.3765. Min Range: -1.3765

Max Act: 1.1427. Min Act: -0.0001

Data Index: 1519791 (Python Code)

Max Activating Token Index: 419

Text #11

Max Range: 1.3765. Min Range: -1.3765

Max Act: 0.9862. Min Act: -0.0001

Data Index: 1653493 (Python Code)

Max Activating Token Index: 942

Text #12

Max Range: 1.3765. Min Range: -1.3765

Max Act: 1.0184. Min Act: -0.0001

Data Index: 1534389 (Python Code)

Max Activating Token Index: 601

Text #13

Max Range: 1.3765. Min Range: -1.3765

Max Act: 1.0485. Min Act: -0.0001

Data Index: 1400398 (Python Code)

Max Activating Token Index: 860

Text #14

Max Range: 1.3765. Min Range: -1.3765

Max Act: 1.0731. Min Act: -0.0001

Data Index: 1437527 (Python Code)

Max Activating Token Index: 100

Text #15

Max Range: 1.3765. Min Range: -1.3765

Max Act: 1.0093. Min Act: -0.0001

Data Index: 661993 (C4 (Web Text))

Max Activating Token Index: 528

Text #16

Max Range: 1.3765. Min Range: -1.3765

Max Act: 1.0347. Min Act: -0.0001

Data Index: 1517806 (Python Code)

Max Activating Token Index: 290

Text #17

Max Range: 1.3765. Min Range: -1.3765

Max Act: 0.9677. Min Act: -0.0001

Data Index: 1625780 (Python Code)

Max Activating Token Index: 998

Text #18

Max Range: 1.3765. Min Range: -1.3765

Max Act: 0.9613. Min Act: -0.0001

Data Index: 999817 (C4 (Web Text))

Max Activating Token Index: 262

Text #19

Max Range: 1.3765. Min Range: -1.3765

Max Act: 1.0224. Min Act: -0.0001

Data Index: 1608965 (Python Code)

Max Activating Token Index: 364