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

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

Neuron 1735 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: 0.2632. Min Range: -0.2632

Max Act: 0.2589. Min Act: -0.0001

Data Index: 1071004 (C4 (Web Text))

Max Activating Token Index: 116

Text #1

Max Range: 0.2632. Min Range: -0.2632

Max Act: 0.2632. Min Act: -0.0001

Data Index: 740265 (C4 (Web Text))

Max Activating Token Index: 205

Text #2

Max Range: 0.2632. Min Range: -0.2632

Max Act: 0.2622. Min Act: -0.0001

Data Index: 810126 (C4 (Web Text))

Max Activating Token Index: 23

Text #3

Max Range: 0.2632. Min Range: -0.2632

Max Act: 0.2364. Min Act: -0.0001

Data Index: 695385 (C4 (Web Text))

Max Activating Token Index: 34

Text #4

Max Range: 0.2632. Min Range: -0.2632

Max Act: 0.2509. Min Act: -0.0001

Data Index: 780489 (C4 (Web Text))

Max Activating Token Index: 53

Text #5

Max Range: 0.2632. Min Range: -0.2632

Max Act: 0.2528. Min Act: -0.0001

Data Index: 160926 (C4 (Web Text))

Max Activating Token Index: 73

Text #6

Max Range: 0.2632. Min Range: -0.2632

Max Act: 0.2510. Min Act: -0.0001

Data Index: 1072212 (C4 (Web Text))

Max Activating Token Index: 255

Text #7

Max Range: 0.2632. Min Range: -0.2632

Max Act: 0.2461. Min Act: -0.0001

Data Index: 981161 (C4 (Web Text))

Max Activating Token Index: 405

Text #8

Max Range: 0.2632. Min Range: -0.2632

Max Act: 0.2623. Min Act: -0.0001

Data Index: 638738 (C4 (Web Text))

Max Activating Token Index: 1006

Text #9

Max Range: 0.2632. Min Range: -0.2632

Max Act: 0.2230. Min Act: -0.0001

Data Index: 304124 (C4 (Web Text))

Max Activating Token Index: 47

Text #10

Max Range: 0.2632. Min Range: -0.2632

Max Act: 0.2161. Min Act: -0.0001

Data Index: 448746 (C4 (Web Text))

Max Activating Token Index: 662

Text #11

Max Range: 0.2632. Min Range: -0.2632

Max Act: 0.2348. Min Act: -0.0001

Data Index: 540317 (C4 (Web Text))

Max Activating Token Index: 707

Text #12

Max Range: 0.2632. Min Range: -0.2632

Max Act: 0.2381. Min Act: -0.0001

Data Index: 318014 (C4 (Web Text))

Max Activating Token Index: 446

Text #13

Max Range: 0.2632. Min Range: -0.2632

Max Act: 0.2067. Min Act: -0.0001

Data Index: 798938 (C4 (Web Text))

Max Activating Token Index: 238

Text #14

Max Range: 0.2632. Min Range: -0.2632

Max Act: 0.2354. Min Act: -0.0001

Data Index: 512837 (C4 (Web Text))

Max Activating Token Index: 381

Text #15

Max Range: 0.2632. Min Range: -0.2632

Max Act: 0.2352. Min Act: -0.0001

Data Index: 856891 (C4 (Web Text))

Max Activating Token Index: 103

Text #16

Max Range: 0.2632. Min Range: -0.2632

Max Act: 0.2339. Min Act: -0.0001

Data Index: 1042024 (C4 (Web Text))

Max Activating Token Index: 246

Text #17

Max Range: 0.2632. Min Range: -0.2632

Max Act: 0.2257. Min Act: -0.0001

Data Index: 234142 (C4 (Web Text))

Max Activating Token Index: 374

Text #18

Max Range: 0.2632. Min Range: -0.2632

Max Act: 0.2392. Min Act: -0.0001

Data Index: 873319 (C4 (Web Text))

Max Activating Token Index: 760

Text #19

Max Range: 0.2632. Min Range: -0.2632

Max Act: 0.2402. Min Act: -0.0001

Data Index: 108868 (C4 (Web Text))

Max Activating Token Index: 388