Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1611 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.4507. Min Range: -0.4507

Max Act: 0.4507. Min Act: -0.0001

Data Index: 170978 (C4 (Web Text))

Max Activating Token Index: 1012

Text #1

Max Range: 0.4507. Min Range: -0.4507

Max Act: 0.3310. Min Act: -0.0001

Data Index: 909193 (C4 (Web Text))

Max Activating Token Index: 587

Text #2

Max Range: 0.4507. Min Range: -0.4507

Max Act: 0.2965. Min Act: -0.0001

Data Index: 730491 (C4 (Web Text))

Max Activating Token Index: 501

Text #3

Max Range: 0.4507. Min Range: -0.4507

Max Act: 0.2849. Min Act: -0.0001

Data Index: 661860 (C4 (Web Text))

Max Activating Token Index: 322

Text #4

Max Range: 0.4507. Min Range: -0.4507

Max Act: 0.2829. Min Act: -0.0001

Data Index: 1084383 (C4 (Web Text))

Max Activating Token Index: 216

Text #5

Max Range: 0.4507. Min Range: -0.4507

Max Act: 0.2719. Min Act: -0.0001

Data Index: 1319676 (C4 (Web Text))

Max Activating Token Index: 415

Text #6

Max Range: 0.4507. Min Range: -0.4507

Max Act: 0.2691. Min Act: -0.0001

Data Index: 314370 (C4 (Web Text))

Max Activating Token Index: 86

Text #7

Max Range: 0.4507. Min Range: -0.4507

Max Act: 0.2783. Min Act: -0.0001

Data Index: 221814 (C4 (Web Text))

Max Activating Token Index: 41

Text #8

Max Range: 0.4507. Min Range: -0.4507

Max Act: 0.2514. Min Act: -0.0001

Data Index: 1616510 (Python Code)

Max Activating Token Index: 894

Text #9

Max Range: 0.4507. Min Range: -0.4507

Max Act: 0.2530. Min Act: -0.0001

Data Index: 1074100 (C4 (Web Text))

Max Activating Token Index: 956

Text #10

Max Range: 0.4507. Min Range: -0.4507

Max Act: 0.2458. Min Act: -0.0001

Data Index: 1570897 (Python Code)

Max Activating Token Index: 642

Text #11

Max Range: 0.4507. Min Range: -0.4507

Max Act: 0.2484. Min Act: -0.0001

Data Index: 993348 (C4 (Web Text))

Max Activating Token Index: 196

Text #12

Max Range: 0.4507. Min Range: -0.4507

Max Act: 0.2509. Min Act: -0.0001

Data Index: 1362385 (Python Code)

Max Activating Token Index: 685

Text #13

Max Range: 0.4507. Min Range: -0.4507

Max Act: 0.2401. Min Act: -0.0001

Data Index: 1397637 (Python Code)

Max Activating Token Index: 839

Text #14

Max Range: 0.4507. Min Range: -0.4507

Max Act: 0.2281. Min Act: -0.0001

Data Index: 1548797 (Python Code)

Max Activating Token Index: 935

Text #15

Max Range: 0.4507. Min Range: -0.4507

Max Act: 0.2340. Min Act: -0.0001

Data Index: 608421 (C4 (Web Text))

Max Activating Token Index: 637

Text #16

Max Range: 0.4507. Min Range: -0.4507

Max Act: 0.2327. Min Act: -0.0001

Data Index: 599053 (C4 (Web Text))

Max Activating Token Index: 814

Text #17

Max Range: 0.4507. Min Range: -0.4507

Max Act: 0.2497. Min Act: -0.0001

Data Index: 1411216 (Python Code)

Max Activating Token Index: 853

Text #18

Max Range: 0.4507. Min Range: -0.4507

Max Act: 0.2346. Min Act: -0.0001

Data Index: 1587032 (Python Code)

Max Activating Token Index: 960

Text #19

Max Range: 0.4507. Min Range: -0.4507

Max Act: 0.2284. Min Act: -0.0001

Data Index: 1487025 (Python Code)

Max Activating Token Index: 685