Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5568 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.2103. Min Range: -0.2103

Max Act: 0.2103. Min Act: -0.0000

Data Index: 220909 (C4 (Web Text))

Max Activating Token Index: 268

Text #1

Max Range: 0.2103. Min Range: -0.2103

Max Act: 0.1929. Min Act: -0.0000

Data Index: 740120 (C4 (Web Text))

Max Activating Token Index: 142

Text #2

Max Range: 0.2103. Min Range: -0.2103

Max Act: 0.1786. Min Act: -0.0000

Data Index: 962438 (C4 (Web Text))

Max Activating Token Index: 821

Text #3

Max Range: 0.2103. Min Range: -0.2103

Max Act: 0.1750. Min Act: -0.0000

Data Index: 50795 (C4 (Web Text))

Max Activating Token Index: 512

Text #4

Max Range: 0.2103. Min Range: -0.2103

Max Act: 0.1697. Min Act: -0.0000

Data Index: 345756 (C4 (Web Text))

Max Activating Token Index: 38

Text #5

Max Range: 0.2103. Min Range: -0.2103

Max Act: 0.1661. Min Act: -0.0001

Data Index: 650863 (C4 (Web Text))

Max Activating Token Index: 51

Text #6

Max Range: 0.2103. Min Range: -0.2103

Max Act: 0.1548. Min Act: -0.0000

Data Index: 590118 (C4 (Web Text))

Max Activating Token Index: 844

Text #7

Max Range: 0.2103. Min Range: -0.2103

Max Act: 0.1668. Min Act: -0.0000

Data Index: 1110795 (C4 (Web Text))

Max Activating Token Index: 658

Text #8

Max Range: 0.2103. Min Range: -0.2103

Max Act: 0.1608. Min Act: -0.0000

Data Index: 430172 (C4 (Web Text))

Max Activating Token Index: 170

Text #9

Max Range: 0.2103. Min Range: -0.2103

Max Act: 0.1709. Min Act: -0.0000

Data Index: 1202060 (C4 (Web Text))

Max Activating Token Index: 705

Text #10

Max Range: 0.2103. Min Range: -0.2103

Max Act: 0.1650. Min Act: -0.0000

Data Index: 858634 (C4 (Web Text))

Max Activating Token Index: 363

Text #11

Max Range: 0.2103. Min Range: -0.2103

Max Act: 0.1648. Min Act: -0.0000

Data Index: 1193952 (C4 (Web Text))

Max Activating Token Index: 241

Text #12

Max Range: 0.2103. Min Range: -0.2103

Max Act: 0.1583. Min Act: -0.0000

Data Index: 417788 (C4 (Web Text))

Max Activating Token Index: 244

Text #13

Max Range: 0.2103. Min Range: -0.2103

Max Act: 0.1577. Min Act: -0.0000

Data Index: 1047904 (C4 (Web Text))

Max Activating Token Index: 640

Text #14

Max Range: 0.2103. Min Range: -0.2103

Max Act: 0.1559. Min Act: -0.0000

Data Index: 148235 (C4 (Web Text))

Max Activating Token Index: 188

Text #15

Max Range: 0.2103. Min Range: -0.2103

Max Act: 0.1501. Min Act: -0.0001

Data Index: 1253248 (C4 (Web Text))

Max Activating Token Index: 584

Text #16

Max Range: 0.2103. Min Range: -0.2103

Max Act: 0.1543. Min Act: -0.0000

Data Index: 589113 (C4 (Web Text))

Max Activating Token Index: 630

Text #17

Max Range: 0.2103. Min Range: -0.2103

Max Act: 0.1540. Min Act: -0.0000

Data Index: 559978 (C4 (Web Text))

Max Activating Token Index: 171

Text #18

Max Range: 0.2103. Min Range: -0.2103

Max Act: 0.1542. Min Act: -0.0000

Data Index: 454307 (C4 (Web Text))

Max Activating Token Index: 638

Text #19

Max Range: 0.2103. Min Range: -0.2103

Max Act: 0.1487. Min Act: -0.0000

Data Index: 367056 (C4 (Web Text))

Max Activating Token Index: 699