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

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

Neuron 2012 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2711. Min Range: -0.2711

Max Act: 0.2711. Min Act: -0.0000

Data Index: 1471088 (Python Code)

Max Activating Token Index: 654

Text #1

Max Range: 0.2711. Min Range: -0.2711

Max Act: 0.1717. Min Act: -0.0000

Data Index: 1530278 (Python Code)

Max Activating Token Index: 156

Text #2

Max Range: 0.2711. Min Range: -0.2711

Max Act: 0.1490. Min Act: -0.0000

Data Index: 1603373 (Python Code)

Max Activating Token Index: 154

Text #3

Max Range: 0.2711. Min Range: -0.2711

Max Act: 0.1630. Min Act: -0.0000

Data Index: 1375792 (Python Code)

Max Activating Token Index: 792

Text #4

Max Range: 0.2711. Min Range: -0.2711

Max Act: 0.1405. Min Act: -0.0000

Data Index: 842027 (C4 (Web Text))

Max Activating Token Index: 706

Text #5

Max Range: 0.2711. Min Range: -0.2711

Max Act: 0.1532. Min Act: -0.0000

Data Index: 304150 (C4 (Web Text))

Max Activating Token Index: 625

Text #6

Max Range: 0.2711. Min Range: -0.2711

Max Act: 0.1533. Min Act: -0.0000

Data Index: 1003947 (C4 (Web Text))

Max Activating Token Index: 312

Text #7

Max Range: 0.2711. Min Range: -0.2711

Max Act: 0.1400. Min Act: -0.0000

Data Index: 306968 (C4 (Web Text))

Max Activating Token Index: 670

Text #8

Max Range: 0.2711. Min Range: -0.2711

Max Act: 0.1441. Min Act: -0.0000

Data Index: 647728 (C4 (Web Text))

Max Activating Token Index: 528

Text #9

Max Range: 0.2711. Min Range: -0.2711

Max Act: 0.1382. Min Act: -0.0000

Data Index: 118435 (C4 (Web Text))

Max Activating Token Index: 94

Text #10

Max Range: 0.2711. Min Range: -0.2711

Max Act: 0.1360. Min Act: -0.0000

Data Index: 440074 (C4 (Web Text))

Max Activating Token Index: 415

Text #11

Max Range: 0.2711. Min Range: -0.2711

Max Act: 0.1416. Min Act: -0.0000

Data Index: 1543929 (Python Code)

Max Activating Token Index: 847

Text #12

Max Range: 0.2711. Min Range: -0.2711

Max Act: 0.1314. Min Act: -0.0000

Data Index: 608478 (C4 (Web Text))

Max Activating Token Index: 207

Text #13

Max Range: 0.2711. Min Range: -0.2711

Max Act: 0.1211. Min Act: -0.0000

Data Index: 1268127 (C4 (Web Text))

Max Activating Token Index: 252

Text #14

Max Range: 0.2711. Min Range: -0.2711

Max Act: 0.1219. Min Act: -0.0000

Data Index: 489683 (C4 (Web Text))

Max Activating Token Index: 444

Text #15

Max Range: 0.2711. Min Range: -0.2711

Max Act: 0.1058. Min Act: -0.0000

Data Index: 518198 (C4 (Web Text))

Max Activating Token Index: 292

Text #16

Max Range: 0.2711. Min Range: -0.2711

Max Act: 0.1142. Min Act: -0.0000

Data Index: 698706 (C4 (Web Text))

Max Activating Token Index: 500

Text #17

Max Range: 0.2711. Min Range: -0.2711

Max Act: 0.1179. Min Act: -0.0000

Data Index: 1645108 (Python Code)

Max Activating Token Index: 267

Text #18

Max Range: 0.2711. Min Range: -0.2711

Max Act: 0.1132. Min Act: -0.0000

Data Index: 1016611 (C4 (Web Text))

Max Activating Token Index: 949

Text #19

Max Range: 0.2711. Min Range: -0.2711

Max Act: 0.1292. Min Act: -0.0000

Data Index: 401984 (C4 (Web Text))

Max Activating Token Index: 209