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

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

Neuron 2390 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: 0.2100. Min Range: -0.2100

Max Act: 0.2100. Min Act: -0.0000

Data Index: 751400 (C4 (Web Text))

Max Activating Token Index: 524

Text #1

Max Range: 0.2100. Min Range: -0.2100

Max Act: 0.1566. Min Act: -0.0000

Data Index: 855256 (C4 (Web Text))

Max Activating Token Index: 772

Text #2

Max Range: 0.2100. Min Range: -0.2100

Max Act: 0.1884. Min Act: -0.0001

Data Index: 1035478 (C4 (Web Text))

Max Activating Token Index: 120

Text #3

Max Range: 0.2100. Min Range: -0.2100

Max Act: 0.1638. Min Act: -0.0000

Data Index: 376372 (C4 (Web Text))

Max Activating Token Index: 959

Text #4

Max Range: 0.2100. Min Range: -0.2100

Max Act: 0.1774. Min Act: -0.0000

Data Index: 153599 (C4 (Web Text))

Max Activating Token Index: 386

Text #5

Max Range: 0.2100. Min Range: -0.2100

Max Act: 0.1525. Min Act: -0.0001

Data Index: 285352 (C4 (Web Text))

Max Activating Token Index: 653

Text #6

Max Range: 0.2100. Min Range: -0.2100

Max Act: 0.1478. Min Act: -0.0001

Data Index: 1210056 (C4 (Web Text))

Max Activating Token Index: 141

Text #7

Max Range: 0.2100. Min Range: -0.2100

Max Act: 0.1461. Min Act: -0.0001

Data Index: 290334 (C4 (Web Text))

Max Activating Token Index: 798

Text #8

Max Range: 0.2100. Min Range: -0.2100

Max Act: 0.1556. Min Act: -0.0000

Data Index: 408699 (C4 (Web Text))

Max Activating Token Index: 166

Text #9

Max Range: 0.2100. Min Range: -0.2100

Max Act: 0.1388. Min Act: -0.0000

Data Index: 370001 (C4 (Web Text))

Max Activating Token Index: 542

Text #10

Max Range: 0.2100. Min Range: -0.2100

Max Act: 0.1433. Min Act: -0.0000

Data Index: 1126377 (C4 (Web Text))

Max Activating Token Index: 294

Text #11

Max Range: 0.2100. Min Range: -0.2100

Max Act: 0.1425. Min Act: -0.0000

Data Index: 258494 (C4 (Web Text))

Max Activating Token Index: 68

Text #12

Max Range: 0.2100. Min Range: -0.2100

Max Act: 0.1206. Min Act: -0.0000

Data Index: 830125 (C4 (Web Text))

Max Activating Token Index: 675

Text #13

Max Range: 0.2100. Min Range: -0.2100

Max Act: 0.1259. Min Act: -0.0000

Data Index: 53238 (C4 (Web Text))

Max Activating Token Index: 150

Text #14

Max Range: 0.2100. Min Range: -0.2100

Max Act: 0.1445. Min Act: -0.0000

Data Index: 840702 (C4 (Web Text))

Max Activating Token Index: 473

Text #15

Max Range: 0.2100. Min Range: -0.2100

Max Act: 0.1464. Min Act: -0.0000

Data Index: 622604 (C4 (Web Text))

Max Activating Token Index: 275

Text #16

Max Range: 0.2100. Min Range: -0.2100

Max Act: 0.1269. Min Act: -0.0001

Data Index: 53659 (C4 (Web Text))

Max Activating Token Index: 803

Text #17

Max Range: 0.2100. Min Range: -0.2100

Max Act: 0.1380. Min Act: -0.0000

Data Index: 266685 (C4 (Web Text))

Max Activating Token Index: 976

Text #18

Max Range: 0.2100. Min Range: -0.2100

Max Act: 0.1319. Min Act: -0.0000

Data Index: 587698 (C4 (Web Text))

Max Activating Token Index: 48

Text #19

Max Range: 0.2100. Min Range: -0.2100

Max Act: 0.1308. Min Act: -0.0000

Data Index: 320430 (C4 (Web Text))

Max Activating Token Index: 905