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

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

Neuron 4940 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0507. Min Act: -0.0001

Data Index: 830065 (C4 (Web Text))

Max Activating Token Index: 248

Text #1

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0488. Min Act: -0.0001

Data Index: 465623 (C4 (Web Text))

Max Activating Token Index: 917

Text #2

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0455. Min Act: -0.0001

Data Index: 408695 (C4 (Web Text))

Max Activating Token Index: 22

Text #3

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0440. Min Act: -0.0001

Data Index: 1254817 (C4 (Web Text))

Max Activating Token Index: 777

Text #4

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0444. Min Act: -0.0001

Data Index: 1002511 (C4 (Web Text))

Max Activating Token Index: 876

Text #5

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0412. Min Act: -0.0001

Data Index: 164601 (C4 (Web Text))

Max Activating Token Index: 584

Text #6

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0444. Min Act: -0.0001

Data Index: 1062542 (C4 (Web Text))

Max Activating Token Index: 57

Text #7

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0422. Min Act: -0.0001

Data Index: 712274 (C4 (Web Text))

Max Activating Token Index: 120

Text #8

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0426. Min Act: -0.0001

Data Index: 1156167 (C4 (Web Text))

Max Activating Token Index: 27

Text #9

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0386. Min Act: -0.0001

Data Index: 702363 (C4 (Web Text))

Max Activating Token Index: 756

Text #10

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0366. Min Act: -0.0001

Data Index: 598060 (C4 (Web Text))

Max Activating Token Index: 472

Text #11

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0407. Min Act: -0.0001

Data Index: 144237 (C4 (Web Text))

Max Activating Token Index: 934

Text #12

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0422. Min Act: -0.0001

Data Index: 784665 (C4 (Web Text))

Max Activating Token Index: 824

Text #13

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0417. Min Act: -0.0001

Data Index: 1337811 (C4 (Web Text))

Max Activating Token Index: 269

Text #14

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0406. Min Act: -0.0001

Data Index: 789231 (C4 (Web Text))

Max Activating Token Index: 555

Text #15

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0365. Min Act: -0.0001

Data Index: 1330911 (C4 (Web Text))

Max Activating Token Index: 244

Text #16

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0366. Min Act: -0.0001

Data Index: 223618 (C4 (Web Text))

Max Activating Token Index: 681

Text #17

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0377. Min Act: -0.0001

Data Index: 1284853 (C4 (Web Text))

Max Activating Token Index: 831

Text #18

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0369. Min Act: -0.0001

Data Index: 686581 (C4 (Web Text))

Max Activating Token Index: 526

Text #19

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0397. Min Act: -0.0001

Data Index: 1179628 (C4 (Web Text))

Max Activating Token Index: 52