Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1767 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.6046. Min Range: -0.6046

Max Act: 0.6046. Min Act: -0.0000

Data Index: 1147434 (C4 (Web Text))

Max Activating Token Index: 284

Text #1

Max Range: 0.6046. Min Range: -0.6046

Max Act: 0.5512. Min Act: -0.0000

Data Index: 75510 (C4 (Web Text))

Max Activating Token Index: 584

Text #2

Max Range: 0.6046. Min Range: -0.6046

Max Act: 0.5453. Min Act: -0.0000

Data Index: 1337411 (C4 (Web Text))

Max Activating Token Index: 481

Text #3

Max Range: 0.6046. Min Range: -0.6046

Max Act: 0.5213. Min Act: -0.0000

Data Index: 299343 (C4 (Web Text))

Max Activating Token Index: 191

Text #4

Max Range: 0.6046. Min Range: -0.6046

Max Act: 0.5094. Min Act: -0.0000

Data Index: 369084 (C4 (Web Text))

Max Activating Token Index: 402

Text #5

Max Range: 0.6046. Min Range: -0.6046

Max Act: 0.5533. Min Act: -0.0000

Data Index: 931990 (C4 (Web Text))

Max Activating Token Index: 580

Text #6

Max Range: 0.6046. Min Range: -0.6046

Max Act: 0.5256. Min Act: -0.0000

Data Index: 89009 (C4 (Web Text))

Max Activating Token Index: 423

Text #7

Max Range: 0.6046. Min Range: -0.6046

Max Act: 0.5161. Min Act: -0.0000

Data Index: 1009730 (C4 (Web Text))

Max Activating Token Index: 573

Text #8

Max Range: 0.6046. Min Range: -0.6046

Max Act: 0.4806. Min Act: -0.0000

Data Index: 442350 (C4 (Web Text))

Max Activating Token Index: 327

Text #9

Max Range: 0.6046. Min Range: -0.6046

Max Act: 0.4614. Min Act: -0.0000

Data Index: 678592 (C4 (Web Text))

Max Activating Token Index: 87

Text #10

Max Range: 0.6046. Min Range: -0.6046

Max Act: 0.4775. Min Act: -0.0000

Data Index: 1207636 (C4 (Web Text))

Max Activating Token Index: 639

Text #11

Max Range: 0.6046. Min Range: -0.6046

Max Act: 0.4547. Min Act: -0.0000

Data Index: 205349 (C4 (Web Text))

Max Activating Token Index: 373

Text #12

Max Range: 0.6046. Min Range: -0.6046

Max Act: 0.4575. Min Act: -0.0000

Data Index: 1228987 (C4 (Web Text))

Max Activating Token Index: 421

Text #13

Max Range: 0.6046. Min Range: -0.6046

Max Act: 0.4513. Min Act: -0.0000

Data Index: 702752 (C4 (Web Text))

Max Activating Token Index: 241

Text #14

Max Range: 0.6046. Min Range: -0.6046

Max Act: 0.4322. Min Act: 0.0000

Data Index: 289645 (C4 (Web Text))

Max Activating Token Index: 1000

Text #15

Max Range: 0.6046. Min Range: -0.6046

Max Act: 0.4454. Min Act: -0.0000

Data Index: 1240235 (C4 (Web Text))

Max Activating Token Index: 513

Text #16

Max Range: 0.6046. Min Range: -0.6046

Max Act: 0.4428. Min Act: -0.0000

Data Index: 794616 (C4 (Web Text))

Max Activating Token Index: 594

Text #17

Max Range: 0.6046. Min Range: -0.6046

Max Act: 0.4389. Min Act: -0.0000

Data Index: 1562587 (Python Code)

Max Activating Token Index: 689

Text #18

Max Range: 0.6046. Min Range: -0.6046

Max Act: 0.4379. Min Act: -0.0000

Data Index: 1040890 (C4 (Web Text))

Max Activating Token Index: 1010

Text #19

Max Range: 0.6046. Min Range: -0.6046

Max Act: 0.4205. Min Act: -0.0000

Data Index: 1449360 (Python Code)

Max Activating Token Index: 813