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

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

Neuron 351 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 1.8169. Min Range: -1.8169

Max Act: 1.8169. Min Act: -0.0002

Data Index: 218953 (C4 (Web Text))

Max Activating Token Index: 45

Text #1

Max Range: 1.8169. Min Range: -1.8169

Max Act: 1.6459. Min Act: -0.0002

Data Index: 123325 (C4 (Web Text))

Max Activating Token Index: 262

Text #2

Max Range: 1.8169. Min Range: -1.8169

Max Act: 1.5011. Min Act: -0.0002

Data Index: 955743 (C4 (Web Text))

Max Activating Token Index: 26

Text #3

Max Range: 1.8169. Min Range: -1.8169

Max Act: 1.5339. Min Act: -0.0002

Data Index: 125657 (C4 (Web Text))

Max Activating Token Index: 348

Text #4

Max Range: 1.8169. Min Range: -1.8169

Max Act: 1.4758. Min Act: -0.0002

Data Index: 1261174 (C4 (Web Text))

Max Activating Token Index: 894

Text #5

Max Range: 1.8169. Min Range: -1.8169

Max Act: 1.4007. Min Act: -0.0002

Data Index: 112486 (C4 (Web Text))

Max Activating Token Index: 39

Text #6

Max Range: 1.8169. Min Range: -1.8169

Max Act: 1.3721. Min Act: -0.0002

Data Index: 136528 (C4 (Web Text))

Max Activating Token Index: 4

Text #7

Max Range: 1.8169. Min Range: -1.8169

Max Act: 1.3721. Min Act: -0.0002

Data Index: 1040253 (C4 (Web Text))

Max Activating Token Index: 4

Text #8

Max Range: 1.8169. Min Range: -1.8169

Max Act: 1.3544. Min Act: -0.0002

Data Index: 25416 (C4 (Web Text))

Max Activating Token Index: 27

Text #9

Max Range: 1.8169. Min Range: -1.8169

Max Act: 1.3699. Min Act: -0.0002

Data Index: 170101 (C4 (Web Text))

Max Activating Token Index: 26

Text #10

Max Range: 1.8169. Min Range: -1.8169

Max Act: 1.3277. Min Act: -0.0002

Data Index: 1327675 (C4 (Web Text))

Max Activating Token Index: 618

Text #11

Max Range: 1.8169. Min Range: -1.8169

Max Act: 1.3216. Min Act: -0.0002

Data Index: 187899 (C4 (Web Text))

Max Activating Token Index: 21

Text #12

Max Range: 1.8169. Min Range: -1.8169

Max Act: 1.3151. Min Act: -0.0002

Data Index: 322836 (C4 (Web Text))

Max Activating Token Index: 29

Text #13

Max Range: 1.8169. Min Range: -1.8169

Max Act: 1.3105. Min Act: -0.0002

Data Index: 185121 (C4 (Web Text))

Max Activating Token Index: 17

Text #14

Max Range: 1.8169. Min Range: -1.8169

Max Act: 1.3426. Min Act: -0.0002

Data Index: 582457 (C4 (Web Text))

Max Activating Token Index: 21

Text #15

Max Range: 1.8169. Min Range: -1.8169

Max Act: 1.3019. Min Act: -0.0002

Data Index: 481973 (C4 (Web Text))

Max Activating Token Index: 2

Text #16

Max Range: 1.8169. Min Range: -1.8169

Max Act: 1.2552. Min Act: -0.0002

Data Index: 1201342 (C4 (Web Text))

Max Activating Token Index: 2

Text #17

Max Range: 1.8169. Min Range: -1.8169

Max Act: 1.2788. Min Act: -0.0002

Data Index: 470147 (C4 (Web Text))

Max Activating Token Index: 15

Text #18

Max Range: 1.8169. Min Range: -1.8169

Max Act: 1.2722. Min Act: -0.0002

Data Index: 17130 (C4 (Web Text))

Max Activating Token Index: 6

Text #19

Max Range: 1.8169. Min Range: -1.8169

Max Act: 1.2207. Min Act: -0.0002

Data Index: 1112522 (C4 (Web Text))

Max Activating Token Index: 794