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

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

Neuron 1920 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0816. Min Act: -0.0004

Data Index: 565822 (C4 (Web Text))

Max Activating Token Index: 259

Text #1

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0663. Min Act: -0.0004

Data Index: 357157 (C4 (Web Text))

Max Activating Token Index: 272

Text #2

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0609. Min Act: -0.0004

Data Index: 850361 (C4 (Web Text))

Max Activating Token Index: 44

Text #3

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0560. Min Act: -0.0004

Data Index: 926540 (C4 (Web Text))

Max Activating Token Index: 252

Text #4

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0548. Min Act: -0.0004

Data Index: 910750 (C4 (Web Text))

Max Activating Token Index: 790

Text #5

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0620. Min Act: -0.0004

Data Index: 668950 (C4 (Web Text))

Max Activating Token Index: 562

Text #6

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0574. Min Act: -0.0004

Data Index: 281660 (C4 (Web Text))

Max Activating Token Index: 566

Text #7

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0537. Min Act: -0.0004

Data Index: 404660 (C4 (Web Text))

Max Activating Token Index: 16

Text #8

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0495. Min Act: -0.0004

Data Index: 191179 (C4 (Web Text))

Max Activating Token Index: 549

Text #9

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0494. Min Act: -0.0004

Data Index: 880818 (C4 (Web Text))

Max Activating Token Index: 779

Text #10

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0485. Min Act: -0.0004

Data Index: 92614 (C4 (Web Text))

Max Activating Token Index: 244

Text #11

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0442. Min Act: -0.0004

Data Index: 1062603 (C4 (Web Text))

Max Activating Token Index: 927

Text #12

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0484. Min Act: -0.0004

Data Index: 546953 (C4 (Web Text))

Max Activating Token Index: 563

Text #13

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0474. Min Act: -0.0004

Data Index: 938966 (C4 (Web Text))

Max Activating Token Index: 19

Text #14

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0468. Min Act: -0.0004

Data Index: 1269484 (C4 (Web Text))

Max Activating Token Index: 334

Text #15

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0446. Min Act: -0.0004

Data Index: 953908 (C4 (Web Text))

Max Activating Token Index: 62

Text #16

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0455. Min Act: -0.0004

Data Index: 854347 (C4 (Web Text))

Max Activating Token Index: 469

Text #17

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0452. Min Act: -0.0004

Data Index: 617195 (C4 (Web Text))

Max Activating Token Index: 450

Text #18

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0447. Min Act: -0.0004

Data Index: 114530 (C4 (Web Text))

Max Activating Token Index: 78

Text #19

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0445. Min Act: -0.0004

Data Index: 300329 (C4 (Web Text))

Max Activating Token Index: 651