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

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

Neuron 3219 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0758. Min Act: -0.0002

Data Index: 1587407 (Python Code)

Max Activating Token Index: 1018

Text #1

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0684. Min Act: -0.0002

Data Index: 1648091 (Python Code)

Max Activating Token Index: 93

Text #2

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0684. Min Act: -0.0002

Data Index: 1506199 (Python Code)

Max Activating Token Index: 428

Text #3

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0512. Min Act: -0.0002

Data Index: 1537266 (Python Code)

Max Activating Token Index: 86

Text #4

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0521. Min Act: -0.0002

Data Index: 1642648 (Python Code)

Max Activating Token Index: 54

Text #5

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0501. Min Act: -0.0002

Data Index: 1650392 (Python Code)

Max Activating Token Index: 70

Text #6

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0498. Min Act: -0.0002

Data Index: 1463116 (Python Code)

Max Activating Token Index: 103

Text #7

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0499. Min Act: -0.0002

Data Index: 1551197 (Python Code)

Max Activating Token Index: 103

Text #8

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0474. Min Act: -0.0002

Data Index: 1525523 (Python Code)

Max Activating Token Index: 856

Text #9

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0474. Min Act: -0.0002

Data Index: 1378747 (Python Code)

Max Activating Token Index: 241

Text #10

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0464. Min Act: -0.0002

Data Index: 1612843 (Python Code)

Max Activating Token Index: 58

Text #11

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0443. Min Act: -0.0002

Data Index: 1374190 (Python Code)

Max Activating Token Index: 164

Text #12

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0438. Min Act: -0.0002

Data Index: 1552798 (Python Code)

Max Activating Token Index: 651

Text #13

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0429. Min Act: -0.0002

Data Index: 1423657 (Python Code)

Max Activating Token Index: 242

Text #14

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0423. Min Act: -0.0002

Data Index: 1376310 (Python Code)

Max Activating Token Index: 228

Text #15

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0416. Min Act: -0.0003

Data Index: 1043954 (C4 (Web Text))

Max Activating Token Index: 38

Text #16

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0416. Min Act: -0.0002

Data Index: 1574425 (Python Code)

Max Activating Token Index: 470

Text #17

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0412. Min Act: -0.0002

Data Index: 364110 (C4 (Web Text))

Max Activating Token Index: 86

Text #18

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0410. Min Act: -0.0002

Data Index: 1506430 (Python Code)

Max Activating Token Index: 394

Text #19

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0411. Min Act: -0.0002

Data Index: 1599715 (Python Code)

Max Activating Token Index: 435