Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2684 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.3396. Min Range: -0.3396

Max Act: 0.3385. Min Act: -0.0001

Data Index: 1475833 (Python Code)

Max Activating Token Index: 493

Text #1

Max Range: 0.3396. Min Range: -0.3396

Max Act: 0.3373. Min Act: -0.0001

Data Index: 929429 (C4 (Web Text))

Max Activating Token Index: 183

Text #2

Max Range: 0.3396. Min Range: -0.3396

Max Act: 0.3396. Min Act: -0.0001

Data Index: 1406456 (Python Code)

Max Activating Token Index: 260

Text #3

Max Range: 0.3396. Min Range: -0.3396

Max Act: 0.3142. Min Act: -0.0001

Data Index: 1409139 (Python Code)

Max Activating Token Index: 280

Text #4

Max Range: 0.3396. Min Range: -0.3396

Max Act: 0.3040. Min Act: -0.0001

Data Index: 1126057 (C4 (Web Text))

Max Activating Token Index: 875

Text #5

Max Range: 0.3396. Min Range: -0.3396

Max Act: 0.3133. Min Act: -0.0001

Data Index: 1508897 (Python Code)

Max Activating Token Index: 304

Text #6

Max Range: 0.3396. Min Range: -0.3396

Max Act: 0.2947. Min Act: -0.0001

Data Index: 1507039 (Python Code)

Max Activating Token Index: 373

Text #7

Max Range: 0.3396. Min Range: -0.3396

Max Act: 0.3095. Min Act: -0.0001

Data Index: 1555346 (Python Code)

Max Activating Token Index: 343

Text #8

Max Range: 0.3396. Min Range: -0.3396

Max Act: 0.2978. Min Act: -0.0001

Data Index: 1639056 (Python Code)

Max Activating Token Index: 425

Text #9

Max Range: 0.3396. Min Range: -0.3396

Max Act: 0.2934. Min Act: -0.0001

Data Index: 1513584 (Python Code)

Max Activating Token Index: 66

Text #10

Max Range: 0.3396. Min Range: -0.3396

Max Act: 0.3208. Min Act: -0.0001

Data Index: 170410 (C4 (Web Text))

Max Activating Token Index: 726

Text #11

Max Range: 0.3396. Min Range: -0.3396

Max Act: 0.2952. Min Act: -0.0001

Data Index: 764939 (C4 (Web Text))

Max Activating Token Index: 554

Text #12

Max Range: 0.3396. Min Range: -0.3396

Max Act: 0.2765. Min Act: -0.0001

Data Index: 1595069 (Python Code)

Max Activating Token Index: 799

Text #13

Max Range: 0.3396. Min Range: -0.3396

Max Act: 0.2842. Min Act: -0.0001

Data Index: 1643599 (Python Code)

Max Activating Token Index: 669

Text #14

Max Range: 0.3396. Min Range: -0.3396

Max Act: 0.2962. Min Act: -0.0001

Data Index: 1612450 (Python Code)

Max Activating Token Index: 432

Text #15

Max Range: 0.3396. Min Range: -0.3396

Max Act: 0.2854. Min Act: -0.0001

Data Index: 1589106 (Python Code)

Max Activating Token Index: 855

Text #16

Max Range: 0.3396. Min Range: -0.3396

Max Act: 0.2657. Min Act: -0.0001

Data Index: 325572 (C4 (Web Text))

Max Activating Token Index: 384

Text #17

Max Range: 0.3396. Min Range: -0.3396

Max Act: 0.2827. Min Act: -0.0001

Data Index: 1417718 (Python Code)

Max Activating Token Index: 280

Text #18

Max Range: 0.3396. Min Range: -0.3396

Max Act: 0.2684. Min Act: -0.0001

Data Index: 1507630 (Python Code)

Max Activating Token Index: 610

Text #19

Max Range: 0.3396. Min Range: -0.3396

Max Act: 0.2749. Min Act: -0.0000

Data Index: 362666 (C4 (Web Text))

Max Activating Token Index: 49