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

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

Neuron 3821 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6131. Min Range: -0.6131

Max Act: 0.6131. Min Act: -0.0002

Data Index: 1428222 (Python Code)

Max Activating Token Index: 614

Text #1

Max Range: 0.6131. Min Range: -0.6131

Max Act: 0.3966. Min Act: -0.0002

Data Index: 1568588 (Python Code)

Max Activating Token Index: 1023

Text #2

Max Range: 0.6131. Min Range: -0.6131

Max Act: 0.0582. Min Act: -0.0002

Data Index: 1462563 (Python Code)

Max Activating Token Index: 851

Text #3

Max Range: 0.6131. Min Range: -0.6131

Max Act: 0.0738. Min Act: -0.0002

Data Index: 1197880 (C4 (Web Text))

Max Activating Token Index: 494

Text #4

Max Range: 0.6131. Min Range: -0.6131

Max Act: 0.0701. Min Act: -0.0002

Data Index: 402582 (C4 (Web Text))

Max Activating Token Index: 548

Text #5

Max Range: 0.6131. Min Range: -0.6131

Max Act: 0.0736. Min Act: -0.0002

Data Index: 1413459 (Python Code)

Max Activating Token Index: 1023

Text #6

Max Range: 0.6131. Min Range: -0.6131

Max Act: 0.0319. Min Act: -0.0002

Data Index: 1592119 (Python Code)

Max Activating Token Index: 645

Text #7

Max Range: 0.6131. Min Range: -0.6131

Max Act: 0.0535. Min Act: -0.0002

Data Index: 216729 (C4 (Web Text))

Max Activating Token Index: 758

Text #8

Max Range: 0.6131. Min Range: -0.6131

Max Act: 0.0565. Min Act: -0.0002

Data Index: 974705 (C4 (Web Text))

Max Activating Token Index: 333

Text #9

Max Range: 0.6131. Min Range: -0.6131

Max Act: 0.0513. Min Act: -0.0002

Data Index: 853659 (C4 (Web Text))

Max Activating Token Index: 832

Text #10

Max Range: 0.6131. Min Range: -0.6131

Max Act: 0.0276. Min Act: -0.0002

Data Index: 1587485 (Python Code)

Max Activating Token Index: 588

Text #11

Max Range: 0.6131. Min Range: -0.6131

Max Act: 0.0473. Min Act: -0.0002

Data Index: 1634796 (Python Code)

Max Activating Token Index: 445

Text #12

Max Range: 0.6131. Min Range: -0.6131

Max Act: 0.0468. Min Act: -0.0002

Data Index: 156616 (C4 (Web Text))

Max Activating Token Index: 816

Text #13

Max Range: 0.6131. Min Range: -0.6131

Max Act: 0.0476. Min Act: -0.0002

Data Index: 1318851 (C4 (Web Text))

Max Activating Token Index: 1004

Text #14

Max Range: 0.6131. Min Range: -0.6131

Max Act: 0.0456. Min Act: -0.0002

Data Index: 1336346 (C4 (Web Text))

Max Activating Token Index: 1007

Text #15

Max Range: 0.6131. Min Range: -0.6131

Max Act: 0.0464. Min Act: -0.0002

Data Index: 346448 (C4 (Web Text))

Max Activating Token Index: 563

Text #16

Max Range: 0.6131. Min Range: -0.6131

Max Act: 0.0452. Min Act: -0.0002

Data Index: 1612139 (Python Code)

Max Activating Token Index: 652

Text #17

Max Range: 0.6131. Min Range: -0.6131

Max Act: 0.0449. Min Act: -0.0002

Data Index: 1544460 (Python Code)

Max Activating Token Index: 973

Text #18

Max Range: 0.6131. Min Range: -0.6131

Max Act: 0.0431. Min Act: -0.0002

Data Index: 1596728 (Python Code)

Max Activating Token Index: 964

Text #19

Max Range: 0.6131. Min Range: -0.6131

Max Act: 0.0429. Min Act: -0.0002

Data Index: 1560512 (Python Code)

Max Activating Token Index: 1023