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

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

Neuron 2713 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0503. Min Act: -0.0003

Data Index: 97390 (C4 (Web Text))

Max Activating Token Index: 99

Text #1

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0495. Min Act: -0.0003

Data Index: 703652 (C4 (Web Text))

Max Activating Token Index: 18

Text #2

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0495. Min Act: -0.0003

Data Index: 346909 (C4 (Web Text))

Max Activating Token Index: 938

Text #3

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0467. Min Act: -0.0003

Data Index: 42072 (C4 (Web Text))

Max Activating Token Index: 18

Text #4

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0486. Min Act: -0.0003

Data Index: 119293 (C4 (Web Text))

Max Activating Token Index: 16

Text #5

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0464. Min Act: -0.0003

Data Index: 1233286 (C4 (Web Text))

Max Activating Token Index: 835

Text #6

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0450. Min Act: -0.0003

Data Index: 32998 (C4 (Web Text))

Max Activating Token Index: 936

Text #7

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0465. Min Act: -0.0003

Data Index: 750024 (C4 (Web Text))

Max Activating Token Index: 927

Text #8

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0461. Min Act: -0.0003

Data Index: 737497 (C4 (Web Text))

Max Activating Token Index: 986

Text #9

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0464. Min Act: -0.0003

Data Index: 810234 (C4 (Web Text))

Max Activating Token Index: 135

Text #10

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0446. Min Act: -0.0003

Data Index: 969355 (C4 (Web Text))

Max Activating Token Index: 881

Text #11

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0478. Min Act: -0.0003

Data Index: 1093469 (C4 (Web Text))

Max Activating Token Index: 16

Text #12

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0464. Min Act: -0.0003

Data Index: 1215797 (C4 (Web Text))

Max Activating Token Index: 19

Text #13

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0436. Min Act: -0.0003

Data Index: 303746 (C4 (Web Text))

Max Activating Token Index: 830

Text #14

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0454. Min Act: -0.0003

Data Index: 1106974 (C4 (Web Text))

Max Activating Token Index: 496

Text #15

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0459. Min Act: -0.0003

Data Index: 370078 (C4 (Web Text))

Max Activating Token Index: 808

Text #16

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0460. Min Act: -0.0003

Data Index: 400196 (C4 (Web Text))

Max Activating Token Index: 970

Text #17

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0475. Min Act: -0.0003

Data Index: 527202 (C4 (Web Text))

Max Activating Token Index: 16

Text #18

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0450. Min Act: -0.0003

Data Index: 242959 (C4 (Web Text))

Max Activating Token Index: 820

Text #19

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0437. Min Act: -0.0003

Data Index: 891632 (C4 (Web Text))

Max Activating Token Index: 893