Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1470 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.5169. Min Range: -0.5169

Max Act: 0.5169. Min Act: -0.0000

Data Index: 1633186 (Python Code)

Max Activating Token Index: 897

Text #1

Max Range: 0.5169. Min Range: -0.5169

Max Act: 0.3652. Min Act: -0.0000

Data Index: 1417476 (Python Code)

Max Activating Token Index: 264

Text #2

Max Range: 0.5169. Min Range: -0.5169

Max Act: 0.4302. Min Act: -0.0000

Data Index: 1091453 (C4 (Web Text))

Max Activating Token Index: 141

Text #3

Max Range: 0.5169. Min Range: -0.5169

Max Act: 0.4117. Min Act: -0.0000

Data Index: 1522893 (Python Code)

Max Activating Token Index: 41

Text #4

Max Range: 0.5169. Min Range: -0.5169

Max Act: 0.3791. Min Act: -0.0000

Data Index: 1110741 (C4 (Web Text))

Max Activating Token Index: 809

Text #5

Max Range: 0.5169. Min Range: -0.5169

Max Act: 0.4314. Min Act: -0.0000

Data Index: 1401866 (Python Code)

Max Activating Token Index: 447

Text #6

Max Range: 0.5169. Min Range: -0.5169

Max Act: 0.4347. Min Act: -0.0000

Data Index: 1571135 (Python Code)

Max Activating Token Index: 109

Text #7

Max Range: 0.5169. Min Range: -0.5169

Max Act: 0.3980. Min Act: -0.0000

Data Index: 1048415 (C4 (Web Text))

Max Activating Token Index: 609

Text #8

Max Range: 0.5169. Min Range: -0.5169

Max Act: 0.3810. Min Act: -0.0000

Data Index: 83374 (C4 (Web Text))

Max Activating Token Index: 1005

Text #9

Max Range: 0.5169. Min Range: -0.5169

Max Act: 0.4388. Min Act: -0.0000

Data Index: 1495482 (Python Code)

Max Activating Token Index: 595

Text #10

Max Range: 0.5169. Min Range: -0.5169

Max Act: 0.4172. Min Act: -0.0000

Data Index: 217996 (C4 (Web Text))

Max Activating Token Index: 123

Text #11

Max Range: 0.5169. Min Range: -0.5169

Max Act: 0.3773. Min Act: -0.0000

Data Index: 1538063 (Python Code)

Max Activating Token Index: 479

Text #12

Max Range: 0.5169. Min Range: -0.5169

Max Act: 0.3724. Min Act: -0.0000

Data Index: 398238 (C4 (Web Text))

Max Activating Token Index: 763

Text #13

Max Range: 0.5169. Min Range: -0.5169

Max Act: 0.4027. Min Act: -0.0000

Data Index: 1404766 (Python Code)

Max Activating Token Index: 1022

Text #14

Max Range: 0.5169. Min Range: -0.5169

Max Act: 0.3722. Min Act: -0.0000

Data Index: 1187822 (C4 (Web Text))

Max Activating Token Index: 23

Text #15

Max Range: 0.5169. Min Range: -0.5169

Max Act: 0.3439. Min Act: -0.0000

Data Index: 1644085 (Python Code)

Max Activating Token Index: 291

Text #16

Max Range: 0.5169. Min Range: -0.5169

Max Act: 0.3250. Min Act: -0.0000

Data Index: 1552014 (Python Code)

Max Activating Token Index: 864

Text #17

Max Range: 0.5169. Min Range: -0.5169

Max Act: 0.4085. Min Act: -0.0000

Data Index: 288436 (C4 (Web Text))

Max Activating Token Index: 1006

Text #18

Max Range: 0.5169. Min Range: -0.5169

Max Act: 0.3985. Min Act: -0.0000

Data Index: 1494670 (Python Code)

Max Activating Token Index: 90

Text #19

Max Range: 0.5169. Min Range: -0.5169

Max Act: 0.3459. Min Act: -0.0000

Data Index: 798018 (C4 (Web Text))

Max Activating Token Index: 955