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

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

Neuron 848 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: 2.6165. Min Range: -2.6165

Max Act: 2.6165. Min Act: -0.0002

Data Index: 417267 (C4 (Web Text))

Max Activating Token Index: 28

Text #1

Max Range: 2.6165. Min Range: -2.6165

Max Act: 2.4935. Min Act: -0.0002

Data Index: 305544 (C4 (Web Text))

Max Activating Token Index: 17

Text #2

Max Range: 2.6165. Min Range: -2.6165

Max Act: 2.5369. Min Act: -0.0002

Data Index: 920633 (C4 (Web Text))

Max Activating Token Index: 28

Text #3

Max Range: 2.6165. Min Range: -2.6165

Max Act: 2.4509. Min Act: -0.0002

Data Index: 415918 (C4 (Web Text))

Max Activating Token Index: 206

Text #4

Max Range: 2.6165. Min Range: -2.6165

Max Act: 2.4115. Min Act: -0.0002

Data Index: 800647 (C4 (Web Text))

Max Activating Token Index: 11

Text #5

Max Range: 2.6165. Min Range: -2.6165

Max Act: 2.4502. Min Act: -0.0002

Data Index: 776098 (C4 (Web Text))

Max Activating Token Index: 187

Text #6

Max Range: 2.6165. Min Range: -2.6165

Max Act: 2.3608. Min Act: -0.0002

Data Index: 988685 (C4 (Web Text))

Max Activating Token Index: 24

Text #7

Max Range: 2.6165. Min Range: -2.6165

Max Act: 2.3926. Min Act: -0.0002

Data Index: 970981 (C4 (Web Text))

Max Activating Token Index: 416

Text #8

Max Range: 2.6165. Min Range: -2.6165

Max Act: 2.3421. Min Act: -0.0002

Data Index: 441558 (C4 (Web Text))

Max Activating Token Index: 22

Text #9

Max Range: 2.6165. Min Range: -2.6165

Max Act: 2.3752. Min Act: -0.0002

Data Index: 1261311 (C4 (Web Text))

Max Activating Token Index: 30

Text #10

Max Range: 2.6165. Min Range: -2.6165

Max Act: 2.3153. Min Act: -0.0002

Data Index: 1055672 (C4 (Web Text))

Max Activating Token Index: 111

Text #11

Max Range: 2.6165. Min Range: -2.6165

Max Act: 2.3234. Min Act: -0.0002

Data Index: 105737 (C4 (Web Text))

Max Activating Token Index: 477

Text #12

Max Range: 2.6165. Min Range: -2.6165

Max Act: 2.3773. Min Act: -0.0002

Data Index: 68950 (C4 (Web Text))

Max Activating Token Index: 9

Text #13

Max Range: 2.6165. Min Range: -2.6165

Max Act: 2.3325. Min Act: -0.0002

Data Index: 929942 (C4 (Web Text))

Max Activating Token Index: 763

Text #14

Max Range: 2.6165. Min Range: -2.6165

Max Act: 2.3129. Min Act: -0.0002

Data Index: 520124 (C4 (Web Text))

Max Activating Token Index: 10

Text #15

Max Range: 2.6165. Min Range: -2.6165

Max Act: 2.3153. Min Act: -0.0002

Data Index: 1270530 (C4 (Web Text))

Max Activating Token Index: 142

Text #16

Max Range: 2.6165. Min Range: -2.6165

Max Act: 2.2936. Min Act: -0.0002

Data Index: 274618 (C4 (Web Text))

Max Activating Token Index: 171

Text #17

Max Range: 2.6165. Min Range: -2.6165

Max Act: 2.2843. Min Act: -0.0002

Data Index: 1041542 (C4 (Web Text))

Max Activating Token Index: 29

Text #18

Max Range: 2.6165. Min Range: -2.6165

Max Act: 2.2230. Min Act: -0.0002

Data Index: 853988 (C4 (Web Text))

Max Activating Token Index: 17

Text #19

Max Range: 2.6165. Min Range: -2.6165

Max Act: 2.2075. Min Act: -0.0002

Data Index: 5111 (C4 (Web Text))

Max Activating Token Index: 343