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

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

Neuron 3677 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6680. Min Range: -3.6680

Max Act: 3.6680. Min Act: -0.0001

Data Index: 677542 (C4 (Web Text))

Max Activating Token Index: 477

Text #1

Max Range: 3.6680. Min Range: -3.6680

Max Act: 3.3804. Min Act: -0.0001

Data Index: 868172 (C4 (Web Text))

Max Activating Token Index: 591

Text #2

Max Range: 3.6680. Min Range: -3.6680

Max Act: 3.0005. Min Act: -0.0001

Data Index: 369219 (C4 (Web Text))

Max Activating Token Index: 571

Text #3

Max Range: 3.6680. Min Range: -3.6680

Max Act: 2.5713. Min Act: -0.0001

Data Index: 91246 (C4 (Web Text))

Max Activating Token Index: 362

Text #4

Max Range: 3.6680. Min Range: -3.6680

Max Act: 2.5223. Min Act: -0.0001

Data Index: 81278 (C4 (Web Text))

Max Activating Token Index: 32

Text #5

Max Range: 3.6680. Min Range: -3.6680

Max Act: 2.4408. Min Act: -0.0001

Data Index: 167287 (C4 (Web Text))

Max Activating Token Index: 538

Text #6

Max Range: 3.6680. Min Range: -3.6680

Max Act: 2.4351. Min Act: -0.0001

Data Index: 999943 (C4 (Web Text))

Max Activating Token Index: 753

Text #7

Max Range: 3.6680. Min Range: -3.6680

Max Act: 2.3051. Min Act: -0.0001

Data Index: 78749 (C4 (Web Text))

Max Activating Token Index: 119

Text #8

Max Range: 3.6680. Min Range: -3.6680

Max Act: 2.1695. Min Act: -0.0001

Data Index: 1198168 (C4 (Web Text))

Max Activating Token Index: 589

Text #9

Max Range: 3.6680. Min Range: -3.6680

Max Act: 2.2989. Min Act: -0.0001

Data Index: 1185855 (C4 (Web Text))

Max Activating Token Index: 1002

Text #10

Max Range: 3.6680. Min Range: -3.6680

Max Act: 2.3259. Min Act: -0.0001

Data Index: 194357 (C4 (Web Text))

Max Activating Token Index: 633

Text #11

Max Range: 3.6680. Min Range: -3.6680

Max Act: 2.3277. Min Act: -0.0001

Data Index: 400552 (C4 (Web Text))

Max Activating Token Index: 324

Text #12

Max Range: 3.6680. Min Range: -3.6680

Max Act: 2.3337. Min Act: -0.0001

Data Index: 549225 (C4 (Web Text))

Max Activating Token Index: 748

Text #13

Max Range: 3.6680. Min Range: -3.6680

Max Act: 2.3160. Min Act: -0.0001

Data Index: 685563 (C4 (Web Text))

Max Activating Token Index: 862

Text #14

Max Range: 3.6680. Min Range: -3.6680

Max Act: 2.3037. Min Act: -0.0001

Data Index: 539389 (C4 (Web Text))

Max Activating Token Index: 579

Text #15

Max Range: 3.6680. Min Range: -3.6680

Max Act: 2.3965. Min Act: -0.0001

Data Index: 1081423 (C4 (Web Text))

Max Activating Token Index: 963

Text #16

Max Range: 3.6680. Min Range: -3.6680

Max Act: 2.1485. Min Act: -0.0001

Data Index: 1101549 (C4 (Web Text))

Max Activating Token Index: 267

Text #17

Max Range: 3.6680. Min Range: -3.6680

Max Act: 2.3702. Min Act: -0.0001

Data Index: 1039423 (C4 (Web Text))

Max Activating Token Index: 336

Text #18

Max Range: 3.6680. Min Range: -3.6680

Max Act: 2.2423. Min Act: -0.0001

Data Index: 321183 (C4 (Web Text))

Max Activating Token Index: 676

Text #19

Max Range: 3.6680. Min Range: -3.6680

Max Act: 2.1824. Min Act: -0.0001

Data Index: 725677 (C4 (Web Text))

Max Activating Token Index: 711