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

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

Neuron 1845 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3445. Min Range: -0.3445

Max Act: 0.3445. Min Act: -0.0001

Data Index: 604309 (C4 (Web Text))

Max Activating Token Index: 901

Text #1

Max Range: 0.3445. Min Range: -0.3445

Max Act: 0.3107. Min Act: -0.0001

Data Index: 1608041 (Python Code)

Max Activating Token Index: 682

Text #2

Max Range: 0.3445. Min Range: -0.3445

Max Act: 0.3213. Min Act: -0.0001

Data Index: 875154 (C4 (Web Text))

Max Activating Token Index: 17

Text #3

Max Range: 0.3445. Min Range: -0.3445

Max Act: 0.2833. Min Act: -0.0001

Data Index: 1637971 (Python Code)

Max Activating Token Index: 72

Text #4

Max Range: 0.3445. Min Range: -0.3445

Max Act: 0.2797. Min Act: -0.0001

Data Index: 1469772 (Python Code)

Max Activating Token Index: 469

Text #5

Max Range: 0.3445. Min Range: -0.3445

Max Act: 0.2804. Min Act: -0.0001

Data Index: 1188210 (C4 (Web Text))

Max Activating Token Index: 377

Text #6

Max Range: 0.3445. Min Range: -0.3445

Max Act: 0.2591. Min Act: -0.0001

Data Index: 718280 (C4 (Web Text))

Max Activating Token Index: 758

Text #7

Max Range: 0.3445. Min Range: -0.3445

Max Act: 0.2685. Min Act: -0.0001

Data Index: 240376 (C4 (Web Text))

Max Activating Token Index: 750

Text #8

Max Range: 0.3445. Min Range: -0.3445

Max Act: 0.2637. Min Act: -0.0001

Data Index: 1442224 (Python Code)

Max Activating Token Index: 41

Text #9

Max Range: 0.3445. Min Range: -0.3445

Max Act: 0.2466. Min Act: -0.0001

Data Index: 1566106 (Python Code)

Max Activating Token Index: 278

Text #10

Max Range: 0.3445. Min Range: -0.3445

Max Act: 0.2527. Min Act: -0.0001

Data Index: 1610079 (Python Code)

Max Activating Token Index: 169

Text #11

Max Range: 0.3445. Min Range: -0.3445

Max Act: 0.2534. Min Act: -0.0001

Data Index: 1516236 (Python Code)

Max Activating Token Index: 107

Text #12

Max Range: 0.3445. Min Range: -0.3445

Max Act: 0.2526. Min Act: -0.0001

Data Index: 1509667 (Python Code)

Max Activating Token Index: 519

Text #13

Max Range: 0.3445. Min Range: -0.3445

Max Act: 0.2427. Min Act: -0.0001

Data Index: 1390077 (Python Code)

Max Activating Token Index: 453

Text #14

Max Range: 0.3445. Min Range: -0.3445

Max Act: 0.2456. Min Act: -0.0001

Data Index: 1377081 (Python Code)

Max Activating Token Index: 827

Text #15

Max Range: 0.3445. Min Range: -0.3445

Max Act: 0.2514. Min Act: -0.0001

Data Index: 296353 (C4 (Web Text))

Max Activating Token Index: 32

Text #16

Max Range: 0.3445. Min Range: -0.3445

Max Act: 0.2429. Min Act: -0.0001

Data Index: 1173300 (C4 (Web Text))

Max Activating Token Index: 503

Text #17

Max Range: 0.3445. Min Range: -0.3445

Max Act: 0.2392. Min Act: -0.0000

Data Index: 578206 (C4 (Web Text))

Max Activating Token Index: 724

Text #18

Max Range: 0.3445. Min Range: -0.3445

Max Act: 0.2455. Min Act: -0.0000

Data Index: 1346537 (C4 (Web Text))

Max Activating Token Index: 926

Text #19

Max Range: 0.3445. Min Range: -0.3445

Max Act: 0.2528. Min Act: -0.0001

Data Index: 1506919 (Python Code)

Max Activating Token Index: 624