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

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

Neuron 607 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2338. Min Range: -0.2338

Max Act: 0.2338. Min Act: -0.0000

Data Index: 81018 (C4 (Web Text))

Max Activating Token Index: 63

Text #1

Max Range: 0.2338. Min Range: -0.2338

Max Act: 0.1665. Min Act: -0.0000

Data Index: 163929 (C4 (Web Text))

Max Activating Token Index: 263

Text #2

Max Range: 0.2338. Min Range: -0.2338

Max Act: 0.1648. Min Act: -0.0000

Data Index: 1135427 (C4 (Web Text))

Max Activating Token Index: 920

Text #3

Max Range: 0.2338. Min Range: -0.2338

Max Act: 0.1632. Min Act: -0.0000

Data Index: 110363 (C4 (Web Text))

Max Activating Token Index: 29

Text #4

Max Range: 0.2338. Min Range: -0.2338

Max Act: 0.1631. Min Act: -0.0000

Data Index: 161925 (C4 (Web Text))

Max Activating Token Index: 772

Text #5

Max Range: 0.2338. Min Range: -0.2338

Max Act: 0.1584. Min Act: -0.0000

Data Index: 762622 (C4 (Web Text))

Max Activating Token Index: 581

Text #6

Max Range: 0.2338. Min Range: -0.2338

Max Act: 0.1565. Min Act: -0.0000

Data Index: 632185 (C4 (Web Text))

Max Activating Token Index: 442

Text #7

Max Range: 0.2338. Min Range: -0.2338

Max Act: 0.1810. Min Act: -0.0000

Data Index: 776683 (C4 (Web Text))

Max Activating Token Index: 204

Text #8

Max Range: 0.2338. Min Range: -0.2338

Max Act: 0.1615. Min Act: -0.0000

Data Index: 1077441 (C4 (Web Text))

Max Activating Token Index: 708

Text #9

Max Range: 0.2338. Min Range: -0.2338

Max Act: 0.1512. Min Act: -0.0000

Data Index: 423411 (C4 (Web Text))

Max Activating Token Index: 103

Text #10

Max Range: 0.2338. Min Range: -0.2338

Max Act: 0.1623. Min Act: -0.0000

Data Index: 1357251 (C4 (Web Text))

Max Activating Token Index: 408

Text #11

Max Range: 0.2338. Min Range: -0.2338

Max Act: 0.1576. Min Act: -0.0000

Data Index: 909108 (C4 (Web Text))

Max Activating Token Index: 164

Text #12

Max Range: 0.2338. Min Range: -0.2338

Max Act: 0.1498. Min Act: -0.0000

Data Index: 65250 (C4 (Web Text))

Max Activating Token Index: 532

Text #13

Max Range: 0.2338. Min Range: -0.2338

Max Act: 0.1398. Min Act: -0.0000

Data Index: 818854 (C4 (Web Text))

Max Activating Token Index: 258

Text #14

Max Range: 0.2338. Min Range: -0.2338

Max Act: 0.1382. Min Act: -0.0000

Data Index: 424157 (C4 (Web Text))

Max Activating Token Index: 98

Text #15

Max Range: 0.2338. Min Range: -0.2338

Max Act: 0.1362. Min Act: -0.0000

Data Index: 538178 (C4 (Web Text))

Max Activating Token Index: 664

Text #16

Max Range: 0.2338. Min Range: -0.2338

Max Act: 0.1353. Min Act: -0.0000

Data Index: 1464465 (Python Code)

Max Activating Token Index: 34

Text #17

Max Range: 0.2338. Min Range: -0.2338

Max Act: 0.1437. Min Act: -0.0000

Data Index: 438394 (C4 (Web Text))

Max Activating Token Index: 429

Text #18

Max Range: 0.2338. Min Range: -0.2338

Max Act: 0.1350. Min Act: -0.0000

Data Index: 468505 (C4 (Web Text))

Max Activating Token Index: 694

Text #19

Max Range: 0.2338. Min Range: -0.2338

Max Act: 0.1342. Min Act: -0.0000

Data Index: 410186 (C4 (Web Text))

Max Activating Token Index: 242