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

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

Neuron 721 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1959. Min Range: -0.1959

Max Act: 0.1959. Min Act: -0.0001

Data Index: 1504018 (Python Code)

Max Activating Token Index: 407

Text #1

Max Range: 0.1959. Min Range: -0.1959

Max Act: 0.1809. Min Act: -0.0001

Data Index: 711900 (C4 (Web Text))

Max Activating Token Index: 907

Text #2

Max Range: 0.1959. Min Range: -0.1959

Max Act: 0.1747. Min Act: -0.0001

Data Index: 1595464 (Python Code)

Max Activating Token Index: 623

Text #3

Max Range: 0.1959. Min Range: -0.1959

Max Act: 0.1739. Min Act: -0.0001

Data Index: 1148216 (C4 (Web Text))

Max Activating Token Index: 958

Text #4

Max Range: 0.1959. Min Range: -0.1959

Max Act: 0.1802. Min Act: -0.0001

Data Index: 1571565 (Python Code)

Max Activating Token Index: 646

Text #5

Max Range: 0.1959. Min Range: -0.1959

Max Act: 0.1621. Min Act: -0.0001

Data Index: 1474894 (Python Code)

Max Activating Token Index: 805

Text #6

Max Range: 0.1959. Min Range: -0.1959

Max Act: 0.1545. Min Act: -0.0001

Data Index: 1396306 (Python Code)

Max Activating Token Index: 715

Text #7

Max Range: 0.1959. Min Range: -0.1959

Max Act: 0.1588. Min Act: -0.0000

Data Index: 445063 (C4 (Web Text))

Max Activating Token Index: 837

Text #8

Max Range: 0.1959. Min Range: -0.1959

Max Act: 0.1640. Min Act: -0.0001

Data Index: 1632762 (Python Code)

Max Activating Token Index: 777

Text #9

Max Range: 0.1959. Min Range: -0.1959

Max Act: 0.1469. Min Act: -0.0001

Data Index: 1374541 (Python Code)

Max Activating Token Index: 1008

Text #10

Max Range: 0.1959. Min Range: -0.1959

Max Act: 0.1423. Min Act: -0.0001

Data Index: 1376709 (Python Code)

Max Activating Token Index: 86

Text #11

Max Range: 0.1959. Min Range: -0.1959

Max Act: 0.1440. Min Act: -0.0000

Data Index: 1525859 (Python Code)

Max Activating Token Index: 380

Text #12

Max Range: 0.1959. Min Range: -0.1959

Max Act: 0.1494. Min Act: -0.0000

Data Index: 1597290 (Python Code)

Max Activating Token Index: 785

Text #13

Max Range: 0.1959. Min Range: -0.1959

Max Act: 0.1318. Min Act: -0.0000

Data Index: 1017670 (C4 (Web Text))

Max Activating Token Index: 892

Text #14

Max Range: 0.1959. Min Range: -0.1959

Max Act: 0.1484. Min Act: -0.0000

Data Index: 1400565 (Python Code)

Max Activating Token Index: 709

Text #15

Max Range: 0.1959. Min Range: -0.1959

Max Act: 0.1382. Min Act: -0.0001

Data Index: 1602676 (Python Code)

Max Activating Token Index: 792

Text #16

Max Range: 0.1959. Min Range: -0.1959

Max Act: 0.1359. Min Act: -0.0001

Data Index: 1628525 (Python Code)

Max Activating Token Index: 402

Text #17

Max Range: 0.1959. Min Range: -0.1959

Max Act: 0.1343. Min Act: -0.0001

Data Index: 1422258 (Python Code)

Max Activating Token Index: 127

Text #18

Max Range: 0.1959. Min Range: -0.1959

Max Act: 0.1302. Min Act: -0.0001

Data Index: 1650899 (Python Code)

Max Activating Token Index: 684

Text #19

Max Range: 0.1959. Min Range: -0.1959

Max Act: 0.1312. Min Act: -0.0000

Data Index: 1460881 (Python Code)

Max Activating Token Index: 161