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

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

Neuron 1844 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6325. Min Range: -0.6325

Max Act: 0.6312. Min Act: -0.0000

Data Index: 560118 (C4 (Web Text))

Max Activating Token Index: 435

Text #1

Max Range: 0.6325. Min Range: -0.6325

Max Act: 0.6325. Min Act: -0.0000

Data Index: 531927 (C4 (Web Text))

Max Activating Token Index: 233

Text #2

Max Range: 0.6325. Min Range: -0.6325

Max Act: 0.5289. Min Act: -0.0000

Data Index: 684660 (C4 (Web Text))

Max Activating Token Index: 258

Text #3

Max Range: 0.6325. Min Range: -0.6325

Max Act: 0.5163. Min Act: -0.0000

Data Index: 142930 (C4 (Web Text))

Max Activating Token Index: 224

Text #4

Max Range: 0.6325. Min Range: -0.6325

Max Act: 0.5027. Min Act: -0.0000

Data Index: 866555 (C4 (Web Text))

Max Activating Token Index: 733

Text #5

Max Range: 0.6325. Min Range: -0.6325

Max Act: 0.5297. Min Act: -0.0000

Data Index: 850098 (C4 (Web Text))

Max Activating Token Index: 853

Text #6

Max Range: 0.6325. Min Range: -0.6325

Max Act: 0.4991. Min Act: -0.0000

Data Index: 773443 (C4 (Web Text))

Max Activating Token Index: 918

Text #7

Max Range: 0.6325. Min Range: -0.6325

Max Act: 0.4655. Min Act: -0.0000

Data Index: 736281 (C4 (Web Text))

Max Activating Token Index: 28

Text #8

Max Range: 0.6325. Min Range: -0.6325

Max Act: 0.4598. Min Act: -0.0000

Data Index: 1176270 (C4 (Web Text))

Max Activating Token Index: 447

Text #9

Max Range: 0.6325. Min Range: -0.6325

Max Act: 0.4830. Min Act: -0.0000

Data Index: 548864 (C4 (Web Text))

Max Activating Token Index: 365

Text #10

Max Range: 0.6325. Min Range: -0.6325

Max Act: 0.4309. Min Act: -0.0000

Data Index: 470899 (C4 (Web Text))

Max Activating Token Index: 131

Text #11

Max Range: 0.6325. Min Range: -0.6325

Max Act: 0.4068. Min Act: -0.0000

Data Index: 822258 (C4 (Web Text))

Max Activating Token Index: 159

Text #12

Max Range: 0.6325. Min Range: -0.6325

Max Act: 0.4026. Min Act: -0.0000

Data Index: 573308 (C4 (Web Text))

Max Activating Token Index: 521

Text #13

Max Range: 0.6325. Min Range: -0.6325

Max Act: 0.3549. Min Act: -0.0000

Data Index: 449160 (C4 (Web Text))

Max Activating Token Index: 232

Text #14

Max Range: 0.6325. Min Range: -0.6325

Max Act: 0.3896. Min Act: -0.0000

Data Index: 1355939 (C4 (Web Text))

Max Activating Token Index: 207

Text #15

Max Range: 0.6325. Min Range: -0.6325

Max Act: 0.3353. Min Act: -0.0000

Data Index: 836271 (C4 (Web Text))

Max Activating Token Index: 212

Text #16

Max Range: 0.6325. Min Range: -0.6325

Max Act: 0.3685. Min Act: -0.0000

Data Index: 904883 (C4 (Web Text))

Max Activating Token Index: 389

Text #17

Max Range: 0.6325. Min Range: -0.6325

Max Act: 0.3819. Min Act: -0.0000

Data Index: 275643 (C4 (Web Text))

Max Activating Token Index: 418

Text #18

Max Range: 0.6325. Min Range: -0.6325

Max Act: 0.3781. Min Act: -0.0000

Data Index: 92370 (C4 (Web Text))

Max Activating Token Index: 161

Text #19

Max Range: 0.6325. Min Range: -0.6325

Max Act: 0.3568. Min Act: -0.0000

Data Index: 630082 (C4 (Web Text))

Max Activating Token Index: 313